brooklyn-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From aleds...@apache.org
Subject [5/6] git commit: Support for cassandra v2 and vnodes
Date Tue, 05 Aug 2014 20:43:55 GMT
Support for cassandra v2 and vnodes

- adds USE_VNODES config for v1.2 and v2
- adds numTokensPerNode config
- adds checkForAndInstllJava7or8
- make AstyanaxSupport more robust for testing


Project: http://git-wip-us.apache.org/repos/asf/incubator-brooklyn/repo
Commit: http://git-wip-us.apache.org/repos/asf/incubator-brooklyn/commit/46bf6ff4
Tree: http://git-wip-us.apache.org/repos/asf/incubator-brooklyn/tree/46bf6ff4
Diff: http://git-wip-us.apache.org/repos/asf/incubator-brooklyn/diff/46bf6ff4

Branch: refs/heads/master
Commit: 46bf6ff412fca1e5fa50c78b449077a42b7f89a3
Parents: 7d2d42b
Author: Aled Sage <aled.sage@gmail.com>
Authored: Wed Jul 16 15:39:42 2014 +0100
Committer: Aled Sage <aled.sage@gmail.com>
Committed: Tue Aug 5 16:08:18 2014 +0100

----------------------------------------------------------------------
 .../java/brooklyn/entity/basic/Entities.java    |  10 +
 .../brooklyn/util/text/TemplateProcessor.java   |   2 +-
 .../java/JavaSoftwareProcessSshDriver.java      |  21 +-
 .../nosql/cassandra/CassandraDatacenter.java    |  11 +
 .../cassandra/CassandraDatacenterImpl.java      |  38 +-
 .../entity/nosql/cassandra/CassandraNode.java   |  40 +-
 .../nosql/cassandra/CassandraNodeImpl.java      | 112 ++-
 .../nosql/cassandra/CassandraNodeSshDriver.java |  17 +-
 .../entity/nosql/cassandra/TokenGenerator.java  |   2 +
 .../entity/nosql/cassandra/TokenGenerators.java |  10 +
 .../entity/nosql/cassandra/cassandra-1.2.yaml   | 661 +++++++++++++++++
 .../entity/nosql/cassandra/cassandra-2.0.yaml   | 705 +++++++++++++++++++
 .../entity/nosql/cassandra/cassandra.yaml       | 661 -----------------
 .../entity/nosql/cassandra/AstyanaxSupport.java |  53 +-
 .../CassandraDatacenterIntegrationTest.java     |  83 ++-
 .../cassandra/CassandraDatacenterLiveTest.java  | 260 ++++---
 ...assandraDatacenterRebindIntegrationTest.java |  77 +-
 .../cassandra/CassandraDatacenterTest.java      |  38 +-
 .../cassandra/CassandraNodeIntegrationTest.java |  66 ++
 .../java/brooklyn/test/EntityTestUtils.java     |   6 +
 .../java/brooklyn/util/math/MathPredicates.java |  58 ++
 .../brooklyn/util/math/MathPredicatesTest.java  |  55 ++
 22 files changed, 2093 insertions(+), 893 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/incubator-brooklyn/blob/46bf6ff4/core/src/main/java/brooklyn/entity/basic/Entities.java
----------------------------------------------------------------------
diff --git a/core/src/main/java/brooklyn/entity/basic/Entities.java b/core/src/main/java/brooklyn/entity/basic/Entities.java
index 8cca783..ebb76bb 100644
--- a/core/src/main/java/brooklyn/entity/basic/Entities.java
+++ b/core/src/main/java/brooklyn/entity/basic/Entities.java
@@ -810,11 +810,21 @@ public class Entities {
         }
         return url;
     }
+    
     /** as {@link #getRequiredUrlConfig(Entity, ConfigKey)} */
     public static String getRequiredUrlConfig(Entity entity, HasConfigKey<String> urlKey) {
         return getRequiredUrlConfig(entity, urlKey.getConfigKey());
     }
     
+    /** fails-fast if value of the given URL is null or unresolveable */
+    public static String checkRequiredUrl(Entity entity, String url) {
+        Preconditions.checkNotNull(url, "url");
+        if (!ResourceUtils.create(entity).doesUrlExist(url)) {
+            throw new IllegalStateException(String.format("URL %s on %s is unavailable", url, entity));
+        }
+        return url;
+    }
+
     /** submits a task factory to construct its task at the entity (in a precursor task) and then to submit it;
      * important if e.g. task construction relies on an entity being in scope (in tags, via {@link BrooklynTaskTags}) */
     public static <T extends TaskAdaptable<?>> T submit(final Entity entity, final TaskFactory<T> taskFactory) {

http://git-wip-us.apache.org/repos/asf/incubator-brooklyn/blob/46bf6ff4/core/src/main/java/brooklyn/util/text/TemplateProcessor.java
----------------------------------------------------------------------
diff --git a/core/src/main/java/brooklyn/util/text/TemplateProcessor.java b/core/src/main/java/brooklyn/util/text/TemplateProcessor.java
index 64eb2cd..747c9a9 100644
--- a/core/src/main/java/brooklyn/util/text/TemplateProcessor.java
+++ b/core/src/main/java/brooklyn/util/text/TemplateProcessor.java
@@ -93,7 +93,7 @@ public class TemplateProcessor {
     public static String processTemplateContents(String templateContents, EntityInternal entity, Map<String,? extends Object> extraSubstitutions) {
         ImmutableMap.Builder<String, Object> builder = ImmutableMap.<String, Object>builder()
                 .put("javaSysProps", System.getProperties())
-                .putAll(entity.getApplication().getManagementContext().getConfig().asMapWithStringKeys())
+                .putAll(entity.getManagementContext().getConfig().asMapWithStringKeys())
                 .put("entity", entity)
                 .put("config", entity.getConfigMap().asMapWithStringKeys());
         // TODO might want to look up locations, driver, if available

http://git-wip-us.apache.org/repos/asf/incubator-brooklyn/blob/46bf6ff4/software/base/src/main/java/brooklyn/entity/java/JavaSoftwareProcessSshDriver.java
----------------------------------------------------------------------
diff --git a/software/base/src/main/java/brooklyn/entity/java/JavaSoftwareProcessSshDriver.java b/software/base/src/main/java/brooklyn/entity/java/JavaSoftwareProcessSshDriver.java
index 47d633a..95ed43b 100644
--- a/software/base/src/main/java/brooklyn/entity/java/JavaSoftwareProcessSshDriver.java
+++ b/software/base/src/main/java/brooklyn/entity/java/JavaSoftwareProcessSshDriver.java
@@ -275,7 +275,7 @@ public abstract class JavaSoftwareProcessSshDriver extends AbstractSoftwareProce
      */
     protected boolean checkForAndInstallJava6or7() {
         Optional<String> version = getCurrentJavaVersion();
-        if (version.isPresent() && (version.get().startsWith("1.7") || version.get().startsWith("1.6"))) {
+        if (version.isPresent() && (version.get().startsWith("1.8") || version.get().startsWith("1.7") || version.get().startsWith("1.6"))) {
             log.debug("Java version {} already installed at {}@{}", new Object[]{version.get(), getEntity(), getLocation()});
             return true;
         } else {
@@ -289,6 +289,25 @@ public abstract class JavaSoftwareProcessSshDriver extends AbstractSoftwareProce
     }
 
     /**
+     * Checks for the presence of Java 7 or 8 on the entity's location, installing if necessary.
+     * @return true if Java 7 or 8 was found on the machine or if it was installed correctly, otherwise false.
+     */
+    protected boolean checkForAndInstallJava7or8() {
+        Optional<String> version = getCurrentJavaVersion();
+        if (version.isPresent() && (version.get().startsWith("1.8") || version.get().startsWith("1.7"))) {
+            log.debug("Java version {} already installed at {}@{}", new Object[]{version.get(), getEntity(), getLocation()});
+            return true;
+        } else {
+            // Let's hope not!
+            if (version.isPresent()) {
+                log.debug("Found old Java version {} on {}@{}. Going to install latest Java version.",
+                        new Object[]{version.get(), getEntity(), getLocation()});
+            }
+            return tryJavaInstall("latest", BashCommands.installJava7OrFail()) == 0;
+        }
+    }
+
+    /**
      * Checks for the presence of Java 6 on the entity's location, installing if necessary.
      * @return true if Java 6 was found on the machine or if it was installed correctly, otherwise false.
      */

http://git-wip-us.apache.org/repos/asf/incubator-brooklyn/blob/46bf6ff4/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraDatacenter.java
----------------------------------------------------------------------
diff --git a/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraDatacenter.java b/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraDatacenter.java
index acab113..dfad45d 100644
--- a/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraDatacenter.java
+++ b/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraDatacenter.java
@@ -84,8 +84,19 @@ public interface CassandraDatacenter extends DynamicCluster, DatastoreMixins.Has
         + "useful when configuring multiple datacenters which should be shifted; "
         + "if not set, a random shift is applied. (Pass 0 to prevent any shift.)", null);
 
+    ConfigKey<Boolean> USE_VNODES = ConfigKeys.newBooleanConfigKey(
+            "cassandra.cluster.useVnodes",
+            "Determines whether to use vnodes; if doing so, tokens will not be explicitly assigned to nodes in the cluster",
+            false);
 
     /**
+     * num_tokens will automatically be reset to 1 for each node if {@link #USE_VNODES} is false. 
+     */
+    ConfigKey<Integer> NUM_TOKENS_PER_NODE = ConfigKeys.newIntegerConfigKey("cassandra.numTokensPerNode",
+            "Number of tokens per node; if using vnodes, should set this to a value like 256; will be overridden to 1 if USE_VNODES==false",
+            256);
+    
+    /**
      * Additional time after the nodes in the cluster are up when starting
      * before announcing the cluster as up.
      * <p>

http://git-wip-us.apache.org/repos/asf/incubator-brooklyn/blob/46bf6ff4/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraDatacenterImpl.java
----------------------------------------------------------------------
diff --git a/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraDatacenterImpl.java b/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraDatacenterImpl.java
index 907a055..cf160b1 100644
--- a/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraDatacenterImpl.java
+++ b/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraDatacenterImpl.java
@@ -229,6 +229,10 @@ public class CassandraDatacenterImpl extends DynamicClusterImpl implements Cassa
         return (seedSupplier == null) ? defaultSeedSupplier : seedSupplier;
     }
     
+    protected boolean useVnodes() {
+        return Boolean.TRUE.equals(getConfig(USE_VNODES));
+    }
+    
     protected synchronized TokenGenerator getTokenGenerator() {
         if (tokenGenerator!=null) 
             return tokenGenerator;
@@ -281,20 +285,34 @@ public class CassandraDatacenterImpl extends DynamicClusterImpl implements Cassa
 
     @Override
     public Collection<Entity> grow(int delta) {
-        if (getCurrentSize() == 0) {
-            getTokenGenerator().growingCluster(delta);
+        if (useVnodes()) {
+            // nothing to do for token generator
+        } else {
+            if (getCurrentSize() == 0) {
+                getTokenGenerator().growingCluster(delta);
+            }
         }
         return super.grow(delta);
     }
     
     @Override
     protected Entity createNode(@Nullable Location loc, Map<?,?> flags) {
-        Map<?,?> allflags; 
-        if (flags.containsKey(CassandraNode.TOKEN) || flags.containsKey("token")) {
-            allflags = flags;
-        } else {
+        Map<Object, Object> allflags = MutableMap.copyOf(flags);
+        
+        if ((flags.containsKey(CassandraNode.TOKEN) || flags.containsKey("token")) || (flags.containsKey(CassandraNode.TOKENS) || flags.containsKey("tokens"))) {
+            // leave token config as-is
+        } else if (!useVnodes()) {
             BigInteger token = getTokenGenerator().newToken();
-            allflags = (token == null) ? flags : MutableMap.builder().putAll(flags).put(CassandraNode.TOKEN, token).build();
+            allflags.put(CassandraNode.TOKEN, token);
+        }
+
+        if ((flags.containsKey(CassandraNode.NUM_TOKENS_PER_NODE) || flags.containsKey("numTokensPerNode"))) {
+            // leave num_tokens as-is
+        } else if (useVnodes()) {
+            Integer numTokensPerNode = getConfig(NUM_TOKENS_PER_NODE);
+            allflags.put(CassandraNode.NUM_TOKENS_PER_NODE, numTokensPerNode);
+        } else {
+            allflags.put(CassandraNode.NUM_TOKENS_PER_NODE, 1);
         }
         
         return super.createNode(loc, allflags);
@@ -302,9 +320,9 @@ public class CassandraDatacenterImpl extends DynamicClusterImpl implements Cassa
 
     @Override
     protected Entity replaceMember(Entity member, Location memberLoc, Map<?, ?> extraFlags) {
-        BigInteger oldToken = ((CassandraNode) member).getToken();
-        BigInteger newToken = (oldToken != null) ? getTokenGenerator().getTokenForReplacementNode(oldToken) : null;
-        return super.replaceMember(member, memberLoc,  MutableMap.copyOf(extraFlags).add(CassandraNode.TOKEN, newToken));
+        Set<BigInteger> oldTokens = ((CassandraNode) member).getTokens();
+        Set<BigInteger> newTokens = (oldTokens != null && oldTokens.size() > 0) ? getTokenGenerator().getTokensForReplacementNode(oldTokens) : null;
+        return super.replaceMember(member, memberLoc,  MutableMap.copyOf(extraFlags).add(CassandraNode.TOKENS, newTokens));
     }
 
     @Override

http://git-wip-us.apache.org/repos/asf/incubator-brooklyn/blob/46bf6ff4/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraNode.java
----------------------------------------------------------------------
diff --git a/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraNode.java b/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraNode.java
index fd94d28..996f8ff 100644
--- a/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraNode.java
+++ b/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraNode.java
@@ -40,6 +40,8 @@ import brooklyn.location.basic.PortRanges;
 import brooklyn.util.flags.SetFromFlag;
 import brooklyn.util.time.Duration;
 
+import com.google.common.reflect.TypeToken;
+
 /**
  * An {@link brooklyn.entity.Entity} that represents a Cassandra node in a {@link CassandraDatacenter}.
  */
@@ -99,8 +101,8 @@ public interface CassandraNode extends DatastoreMixins.DatastoreCommon, Software
 
     @SetFromFlag("cassandraConfigTemplateUrl")
     ConfigKey<String> CASSANDRA_CONFIG_TEMPLATE_URL = ConfigKeys.newStringConfigKey(
-            "cassandra.config.templateUrl", "Template file (in freemarker format) for the cassandra.yaml config file", 
-            "classpath://brooklyn/entity/nosql/cassandra/cassandra.yaml");
+            "cassandra.config.templateUrl", "A URL (in freemarker format) for a cassandra.yaml config file (in freemarker format)", 
+            "classpath://brooklyn/entity/nosql/cassandra/cassandra-${entity.majorMinorVersion}.yaml");
 
     @SetFromFlag("cassandraConfigFileName")
     ConfigKey<String> CASSANDRA_CONFIG_FILE_NAME = ConfigKeys.newStringConfigKey(
@@ -125,10 +127,22 @@ public interface CassandraNode extends DatastoreMixins.DatastoreCommon, Software
             String.class, "cassandra.replication.rackName", "Rack name (used for configuring replication, when a suitable snitch is used)", 
             null);
 
+    ConfigKey<Integer> NUM_TOKENS_PER_NODE = ConfigKeys.newIntegerConfigKey("cassandra.numTokensPerNode",
+            "Number of tokens per node; if using vnodes, should set this to a value like 256",
+            1);
+    
+    /**
+     * @deprecated since 0.7; use {@link #TOKENS}
+     */
     @SetFromFlag("token")
+    @Deprecated
     BasicAttributeSensorAndConfigKey<BigInteger> TOKEN = new BasicAttributeSensorAndConfigKey<BigInteger>(
             BigInteger.class, "cassandra.token", "Cassandra Token");
 
+    @SetFromFlag("tokens")
+    BasicAttributeSensorAndConfigKey<Set<BigInteger>> TOKENS = new BasicAttributeSensorAndConfigKey<Set<BigInteger>>(
+            new TypeToken<Set<BigInteger>>() {}, "cassandra.tokens", "Cassandra Tokens");
+
     AttributeSensor<Integer> PEERS = Sensors.newIntegerSensor( "cassandra.peers", "Number of peers in cluster");
 
     AttributeSensor<Integer> LIVE_NODE_COUNT = Sensors.newIntegerSensor( "cassandra.liveNodeCount", "Number of live nodes in cluster");
@@ -166,6 +180,7 @@ public interface CassandraNode extends DatastoreMixins.DatastoreCommon, Software
 
     /* Accessors used from template */
     
+    String getMajorMinorVersion();
     Integer getGossipPort();
     Integer getSslGossipPort();
     Integer getThriftPort();
@@ -179,11 +194,28 @@ public interface CassandraNode extends DatastoreMixins.DatastoreCommon, Software
     String getPrivateIp();
     String getPublicIp();
     
-    /** in range 0 to (2^127)-1; or null if not yet set or known */
+    /**
+     * In range 0 to (2^127)-1; or null if not yet set or known.
+     * Returns the first token if more than one token.
+     * @deprecated since 0.7; see {@link #getTokens()}
+     */
+    @Deprecated
     BigInteger getToken();
-    /** string value of token (with no commas, which freemarker introduces!) or blank if none */
+
+    int getNumTokensPerNode();
+
+    Set<BigInteger> getTokens();
+
+    /**
+     * string value of token (with no commas, which freemarker introduces!) or blank if none
+     * @deprecated since 0.7; use {@link #getTokensAsString()}
+     */
+    @Deprecated
     String getTokenAsString();
 
+    /** string value of comma-separated tokens; or blank if none */
+    String getTokensAsString();
+
     /* For configuration */
     
     void setToken(String token);

http://git-wip-us.apache.org/repos/asf/incubator-brooklyn/blob/46bf6ff4/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraNodeImpl.java
----------------------------------------------------------------------
diff --git a/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraNodeImpl.java b/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraNodeImpl.java
index 0671678..ba3be07 100644
--- a/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraNodeImpl.java
+++ b/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraNodeImpl.java
@@ -61,16 +61,22 @@ import brooklyn.util.config.ConfigBag;
 import brooklyn.util.exceptions.Exceptions;
 import brooklyn.util.guava.Maybe;
 import brooklyn.util.text.Strings;
+import brooklyn.util.text.TemplateProcessor;
 import brooklyn.util.time.Duration;
 
 import com.google.common.base.Function;
 import com.google.common.base.Functions;
+import com.google.common.base.Joiner;
 import com.google.common.base.Predicate;
 import com.google.common.base.Predicates;
+import com.google.common.base.Splitter;
 import com.google.common.base.Throwables;
 import com.google.common.collect.ImmutableList;
+import com.google.common.collect.ImmutableMap;
+import com.google.common.collect.ImmutableSet;
 import com.google.common.collect.Iterables;
 import com.google.common.collect.Maps;
+import com.google.common.collect.Sets;
 
 /**
  * Implementation of {@link CassandraNode}.
@@ -84,6 +90,23 @@ public class CassandraNodeImpl extends SoftwareProcessImpl implements CassandraN
     public CassandraNodeImpl() {
     }
     
+    @Override
+    public void init() {
+        super.init();
+        
+        getMutableEntityType().addEffector(EXECUTE_SCRIPT, new EffectorBody<String>() {
+            @Override
+            public String call(ConfigBag parameters) {
+                return executeScript((String)parameters.getStringKey("commands"));
+            }
+        });
+        
+        Entities.checkRequiredUrl(this, getCassandraConfigTemplateUrl());
+        Entities.getRequiredUrlConfig(this, CASSANDRA_RACKDC_CONFIG_TEMPLATE_URL);
+        
+        connectEnrichers();
+    }
+    
     /**
      * Some clouds (e.g. Rackspace) give us VMs that have two nics: one for private and one for public.
      * If the private IP is used then it doesn't work, even for a cluster purely internal to Rackspace!
@@ -143,12 +166,30 @@ public class CassandraNodeImpl extends SoftwareProcessImpl implements CassandraN
         setCloudPreferredSensorNames();
     }
     
+    // Used for freemarker
+    public String getMajorMinorVersion() {
+        String version = getConfig(CassandraNode.SUGGESTED_VERSION);
+        if (Strings.isBlank(version)) return "";
+        List<String> versionParts = ImmutableList.copyOf(Splitter.on(".").split(version));
+        return versionParts.get(0) + (versionParts.size() > 1 ? "."+versionParts.get(1) : "");
+    }
+    
+    public String getCassandraConfigTemplateUrl() {
+        String templatedUrl = getConfig(CassandraNode.CASSANDRA_CONFIG_TEMPLATE_URL);
+        return TemplateProcessor.processTemplateContents(templatedUrl, this, ImmutableMap.<String, Object>of());
+    }
+
     @Override public Integer getGossipPort() { return getAttribute(CassandraNode.GOSSIP_PORT); }
     @Override public Integer getSslGossipPort() { return getAttribute(CassandraNode.SSL_GOSSIP_PORT); }
     @Override public Integer getThriftPort() { return getAttribute(CassandraNode.THRIFT_PORT); }
     @Override public Integer getNativeTransportPort() { return getAttribute(CassandraNode.NATIVE_TRANSPORT_PORT); }
     @Override public String getClusterName() { return getAttribute(CassandraNode.CLUSTER_NAME); }
     
+    @Override public int getNumTokensPerNode() {
+        return getConfig(CassandraNode.NUM_TOKENS_PER_NODE);
+    }
+
+    @Deprecated
     @Override public BigInteger getToken() {
         BigInteger token = getAttribute(CassandraNode.TOKEN);
         if (token == null) {
@@ -157,12 +198,41 @@ public class CassandraNodeImpl extends SoftwareProcessImpl implements CassandraN
         return token;
     }
     
+    @Override public Set<BigInteger> getTokens() {
+        Set<BigInteger> tokens = getAttribute(CassandraNode.TOKENS);
+        if (tokens == null) {
+            BigInteger token = getAttribute(CassandraNode.TOKEN);
+            if (token != null) {
+                tokens = ImmutableSet.of(token);
+            }
+        }
+        if (tokens == null) {
+            tokens = getAttribute(CassandraNode.TOKENS);
+        }
+        if (tokens == null) {
+            BigInteger token = getAttribute(CassandraNode.TOKEN);
+            if (token != null) {
+                tokens = ImmutableSet.of(token);
+            }
+        }
+        return tokens;
+    }
+    
+    @Deprecated
     @Override public String getTokenAsString() {
         BigInteger token = getToken();
         if (token==null) return "";
         return ""+token;
     }
 
+    @Override public String getTokensAsString() {
+        // TODO check what is required when replacing failed node.
+        // with vnodes in Cassandra 2.x, don't bother supplying token
+        Set<BigInteger> tokens = getTokens();
+        if (tokens == null) return "";
+        return Joiner.on(",").join(tokens);
+    }
+    
     @Override public String getListenAddress() {
         String sensorName = getConfig(LISTEN_ADDRESS_SENSOR);
         if (Strings.isNonBlank(sensorName))
@@ -315,23 +385,6 @@ public class CassandraNodeImpl extends SoftwareProcessImpl implements CassandraN
         return (CassandraNodeDriver) super.getDriver();
     }
 
-    @Override
-    public void init() {
-        super.init();
-        
-        getMutableEntityType().addEffector(EXECUTE_SCRIPT, new EffectorBody<String>() {
-            @Override
-            public String call(ConfigBag parameters) {
-                return executeScript((String)parameters.getStringKey("commands"));
-            }
-        });
-        
-        Entities.getRequiredUrlConfig(this, CASSANDRA_CONFIG_TEMPLATE_URL);
-        Entities.getRequiredUrlConfig(this, CASSANDRA_RACKDC_CONFIG_TEMPLATE_URL);
-        
-        connectEnrichers();
-    }
-    
     private volatile JmxFeed jmxFeed;
     private volatile FunctionFeed functionFeed;
     private JmxFeed jmxMxBeanFeed;
@@ -360,20 +413,37 @@ public class CassandraNodeImpl extends SoftwareProcessImpl implements CassandraN
                         .attributeName("Initialized")
                         .onSuccess(Functions.forPredicate(Predicates.notNull()))
                         .onException(Functions.constant(false)))
+                .pollAttribute(new JmxAttributePollConfig<Set<BigInteger>>(TOKENS)
+                        .objectName(storageServiceMBean)
+                        .attributeName("TokenToEndpointMap")
+                        .onSuccess((Function) new Function<Map, Set<BigInteger>>() {
+                            @Override
+                            public Set<BigInteger> apply(@Nullable Map input) {
+                                if (input == null || input.isEmpty()) return null;
+                                // FIXME does not work on aws-ec2, uses RFC1918 address
+                                Predicate<String> self = Predicates.in(ImmutableList.of(getAttribute(HOSTNAME), getAttribute(ADDRESS), getAttribute(SUBNET_ADDRESS), getAttribute(SUBNET_HOSTNAME)));
+                                Set<String> tokens = Maps.filterValues(input, self).keySet();
+                                Set<BigInteger> result = Sets.newLinkedHashSet();
+                                for (String token : tokens) {
+                                    result.add(new BigInteger(token));
+                                }
+                                return result;
+                            }})
+                        .onException(Functions.<Set<BigInteger>>constant(null)))
                 .pollAttribute(new JmxAttributePollConfig<BigInteger>(TOKEN)
                         .objectName(storageServiceMBean)
                         .attributeName("TokenToEndpointMap")
                         .onSuccess((Function) new Function<Map, BigInteger>() {
                             @Override
                             public BigInteger apply(@Nullable Map input) {
-                                if (input == null || input.isEmpty()) return BigInteger.valueOf(0);
+                                // TODO remove duplication from setting TOKENS
+                                if (input == null || input.isEmpty()) return null;
                                 // FIXME does not work on aws-ec2, uses RFC1918 address
-                                Predicate<String> self = Predicates.in(ImmutableList.of(getAttribute(HOSTNAME), getAttribute(ADDRESS)));
+                                Predicate<String> self = Predicates.in(ImmutableList.of(getAttribute(HOSTNAME), getAttribute(ADDRESS), getAttribute(SUBNET_ADDRESS), getAttribute(SUBNET_HOSTNAME)));
                                 Set<String> tokens = Maps.filterValues(input, self).keySet();
                                 String token = Iterables.getFirst(tokens, null);
                                 return (token != null) ? new BigInteger(token) : null;
-                            }
-                        })
+                            }})
                         .onException(Functions.<BigInteger>constant(null)))
                 .pollOperation(new JmxOperationPollConfig<String>(DATACENTER_NAME)
                         .period(60, TimeUnit.SECONDS)

http://git-wip-us.apache.org/repos/asf/incubator-brooklyn/blob/46bf6ff4/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraNodeSshDriver.java
----------------------------------------------------------------------
diff --git a/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraNodeSshDriver.java b/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraNodeSshDriver.java
index 3701eb4..fc97186 100644
--- a/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraNodeSshDriver.java
+++ b/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/CassandraNodeSshDriver.java
@@ -58,13 +58,13 @@ import brooklyn.util.task.Tasks;
 import brooklyn.util.task.system.ProcessTaskWrapper;
 import brooklyn.util.text.Identifiers;
 import brooklyn.util.text.Strings;
+import brooklyn.util.text.TemplateProcessor;
 import brooklyn.util.time.Duration;
 import brooklyn.util.time.Time;
 
 import com.google.common.collect.ImmutableList;
 import com.google.common.collect.ImmutableMap;
 import com.google.common.collect.ImmutableSet;
-import com.google.common.collect.Sets;
 
 /**
  * Start a {@link CassandraNode} in a {@link Location} accessible over ssh.
@@ -98,7 +98,10 @@ public class CassandraNodeSshDriver extends JavaSoftwareProcessSshDriver impleme
     public String getClusterName() { return entity.getAttribute(CassandraNode.CLUSTER_NAME); }
 
     @Override
-    public String getCassandraConfigTemplateUrl() { return entity.getConfig(CassandraNode.CASSANDRA_CONFIG_TEMPLATE_URL); }
+    public String getCassandraConfigTemplateUrl() {
+        String templatedUrl = entity.getConfig(CassandraNode.CASSANDRA_CONFIG_TEMPLATE_URL);
+        return TemplateProcessor.processTemplateContents(templatedUrl, this, ImmutableMap.<String, Object>of());
+    }
 
     @Override
     public String getCassandraConfigFileName() { return entity.getConfig(CassandraNode.CASSANDRA_CONFIG_FILE_NAME); }
@@ -116,6 +119,16 @@ public class CassandraNodeSshDriver extends JavaSoftwareProcessSshDriver impleme
     }
     
     @Override
+    public boolean installJava() {
+        String version = getVersion();
+        if (version.startsWith("2.")) {
+            return checkForAndInstallJava7or8();
+        } else {
+            return super.installJava();
+        }
+    }
+    
+    @Override
     public void install() {
         log.debug("Installing {}", entity);
         DownloadResolver resolver = Entities.newDownloader(this);

http://git-wip-us.apache.org/repos/asf/incubator-brooklyn/blob/46bf6ff4/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/TokenGenerator.java
----------------------------------------------------------------------
diff --git a/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/TokenGenerator.java b/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/TokenGenerator.java
index e7100e9..8503ad7 100644
--- a/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/TokenGenerator.java
+++ b/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/TokenGenerator.java
@@ -33,6 +33,8 @@ public interface TokenGenerator {
     
     BigInteger getTokenForReplacementNode(BigInteger oldToken);
     
+    Set<BigInteger> getTokensForReplacementNode(Set<BigInteger> oldTokens);
+    
     /**
      * Indicates that we are starting a new cluster of the given number of nodes,
      * so expect that number of consecutive calls to {@link #newToken()}.

http://git-wip-us.apache.org/repos/asf/incubator-brooklyn/blob/46bf6ff4/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/TokenGenerators.java
----------------------------------------------------------------------
diff --git a/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/TokenGenerators.java b/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/TokenGenerators.java
index 90e32f0..70dd0f6 100644
--- a/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/TokenGenerators.java
+++ b/software/nosql/src/main/java/brooklyn/entity/nosql/cassandra/TokenGenerators.java
@@ -80,6 +80,16 @@ public class TokenGenerators {
         }
 
         @Override
+        public synchronized Set<BigInteger> getTokensForReplacementNode(Set<BigInteger> oldTokens) {
+            checkNotNull(oldTokens, "oldToken");
+            Set<BigInteger> result = Sets.newLinkedHashSet();
+            for (BigInteger oldToken : oldTokens) {
+                result.add(getTokenForReplacementNode(oldToken));
+            }
+            return result;
+        }
+        
+        @Override
         public synchronized void growingCluster(int numNewNodes) {
             if (currentTokens.isEmpty() && nextTokens.isEmpty()) {
                 nextTokens.addAll(generateEquidistantTokens(numNewNodes));

http://git-wip-us.apache.org/repos/asf/incubator-brooklyn/blob/46bf6ff4/software/nosql/src/main/resources/brooklyn/entity/nosql/cassandra/cassandra-1.2.yaml
----------------------------------------------------------------------
diff --git a/software/nosql/src/main/resources/brooklyn/entity/nosql/cassandra/cassandra-1.2.yaml b/software/nosql/src/main/resources/brooklyn/entity/nosql/cassandra/cassandra-1.2.yaml
new file mode 100644
index 0000000..09b3f70
--- /dev/null
+++ b/software/nosql/src/main/resources/brooklyn/entity/nosql/cassandra/cassandra-1.2.yaml
@@ -0,0 +1,661 @@
+[#ftl]
+#
+# 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.
+#
+# Cassandra storage config YAML 
+
+# 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: '${entity.clusterName}'
+
+# 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.
+#
+# 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: ${entity.numTokensPerNode?c}
+
+# If you haven't specified num_tokens, or have set it to the default of 1 then
+# you should always specify InitialToken when setting up a production
+# cluster for the first time, and often when adding capacity later.
+# The principle is that each node should be given an equal slice of
+# the token ring; see http://wiki.apache.org/cassandra/Operations
+# for more details.
+#
+# If blank, Cassandra will request a token bisecting the range of
+# the heaviest-loaded existing node.  If there is no load information
+# available, such as is the case with a new cluster, it will pick
+# a random token, which will lead to hot spots.
+initial_token: ${entity.tokensAsString}
+
+# See http://wiki.apache.org/cassandra/HintedHandoff
+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, hints will be dropped.
+max_hint_window_in_ms: 10800000 # 3 hours
+# throttle in KB's per second, per delivery thread
+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
+
+# The following setting populates the page cache on memtable flush and compaction
+# WARNING: Enable this setting only when the whole node's data fits in memory.
+# Defaults to: false
+# populate_io_cache_on_flush: false
+
+# authentication backend, implementing IAuthenticator; used to identify users
+authenticator: org.apache.cassandra.auth.AllowAllAuthenticator
+
+# authorization backend, implementing IAuthorizer; used to limit access/provide permissions
+authorizer: org.apache.cassandra.auth.AllowAllAuthorizer
+
+# The partitioner is responsible for distributing rows (by key) across
+# nodes in the cluster.  Any IPartitioner may be used, including your
+# own as long as it is on the classpath.  Out of the box, Cassandra
+# provides org.apache.cassandra.dht.{Murmur3Partitioner, RandomPartitioner
+# ByteOrderedPartitioner, OrderPreservingPartitioner (deprecated)}.
+# 
+# - RandomPartitioner distributes rows across the cluster evenly by md5.
+#   This is the default prior to 1.2 and is retained for compatibility.
+# - Murmur3Partitioner is similar to RandomPartioner but uses Murmur3_128
+#   Hash Function instead of md5.  When in doubt, this is the best option.
+# - ByteOrderedPartitioner orders rows lexically by key bytes.  BOP allows
+#   scanning rows in key order, but the ordering can generate hot spots
+#   for sequential insertion workloads.
+# - OrderPreservingPartitioner is an obsolete form of BOP, that stores
+# - keys in a less-efficient format and only works with keys that are
+#   UTF8-encoded Strings.
+# - CollatingOPP colates according to EN,US rules rather than lexical byte
+#   ordering.  Use this as an example if you need custom collation.
+#
+# See http://wiki.apache.org/cassandra/Operations for more on
+# partitioners and token selection.
+partitioner: org.apache.cassandra.dht.Murmur3Partitioner
+
+# directories where Cassandra should store data on disk.
+data_file_directories:
+    - ${driver.runDir}/data
+
+# commit log
+commitlog_directory: ${driver.runDir}/commitlog
+
+# policy for data disk failures:
+# stop: shut down gossip and Thrift, leaving the node effectively dead, but
+#       still inspectable via JMX.
+# 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
+
+# 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 store the whole values of
+# its rows, 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
+# safe the keys 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
+# safe 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
+
+# The provider for the row cache to use.
+#
+# Supported values are: ConcurrentLinkedHashCacheProvider, SerializingCacheProvider
+#
+# SerializingCacheProvider serialises the contents of the row and stores
+# it in native memory, i.e., off the JVM Heap. Serialized rows take
+# significantly less memory than "live" rows in the JVM, so you can cache
+# more rows in a given memory footprint.  And storing the cache off-heap
+# means you can use smaller heap sizes, reducing the impact of GC pauses.
+#
+# It is also valid to specify the fully-qualified class name to a class
+# that implements org.apache.cassandra.cache.IRowCacheProvider.
+#
+# Defaults to SerializingCacheProvider
+row_cache_provider: SerializingCacheProvider
+
+# saved caches
+saved_caches_directory: ${driver.runDir}/saved_caches
+
+# commitlog_sync may be either "periodic" or "batch." 
+# When in batch mode, Cassandra won't ack writes until the commit log
+# has been fsynced to disk.  It will wait up to
+# commitlog_sync_batch_window_in_ms milliseconds for other writes, before
+# performing the sync.
+#
+# commitlog_sync: batch
+# commitlog_sync_batch_window_in_ms: 50
+#
+# the other option is "periodic" where writes may be acked immediately
+# and the CommitLog is simply synced every commitlog_sync_period_in_ms
+# milliseconds.
+commitlog_sync: periodic
+commitlog_sync_period_in_ms: 10000
+
+# The size of the individual commitlog file segments.  A commitlog
+# segment may be archived, deleted, or recycled once all the data
+# in it (potentally from each columnfamily in the system) has been 
+# flushed to sstables.  
+#
+# The default size is 32, which is almost always fine, but if you are
+# archiving commitlog segments (see commitlog_archiving.properties),
+# then you probably want a finer granularity of archiving; 8 or 16 MB
+# is reasonable.
+commitlog_segment_size_in_mb: 32
+
+# any class that implements the SeedProvider interface and has a
+# constructor that takes a Map<String, String> of parameters will do.
+seed_provider:
+    # Addresses of hosts that are deemed contact points. 
+    # Cassandra nodes use this list of hosts to find each other and learn
+    # the topology of the ring.  You must change this if you are running
+    # multiple nodes!
+    - class_name: org.apache.cassandra.locator.SimpleSeedProvider
+      parameters:
+          # seeds is actually a comma-delimited list of addresses.
+          # Ex: "<ip1>,<ip2>,<ip3>"
+          - seeds: "${entity.seeds}"
+
+# emergency pressure valve: each time heap usage after a full (CMS)
+# garbage collection is above this fraction of the max, Cassandra will
+# flush the largest memtables.  
+#
+# Set to 1.0 to disable.  Setting this lower than
+# CMSInitiatingOccupancyFraction is not likely to be useful.
+#
+# RELYING ON THIS AS YOUR PRIMARY TUNING MECHANISM WILL WORK POORLY:
+# it is most effective under light to moderate load, or read-heavy
+# workloads; under truly massive write load, it will often be too
+# little, too late.
+flush_largest_memtables_at: 0.75
+
+# emergency pressure valve #2: the first time heap usage after a full
+# (CMS) garbage collection is above this fraction of the max,
+# Cassandra will reduce cache maximum _capacity_ to the given fraction
+# of the current _size_.  Should usually be set substantially above
+# flush_largest_memtables_at, since that will have less long-term
+# impact on the system.  
+# 
+# Set to 1.0 to disable.  Setting this lower than
+# CMSInitiatingOccupancyFraction is not likely to be useful.
+reduce_cache_sizes_at: 0.85
+reduce_cache_capacity_to: 0.6
+
+# 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.
+#
+# 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
+
+# Total memory to use for memtables.  Cassandra will flush the largest
+# memtable when this much memory is used.
+# If omitted, Cassandra will set it to 1/3 of the heap.
+# memtable_total_space_in_mb: 2048
+
+# 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 1024 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: 4096
+
+# 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. If you have a large heap and many data directories,
+# you can increase this value for better flush performance.
+# By default this will be set to the amount of data directories defined.
+#memtable_flush_writers: 1
+
+# the number of full memtables to allow pending flush, that is,
+# waiting for a writer thread.  At a minimum, this should be set to
+# the maximum number of secondary indexes created on a single CF.
+memtable_flush_queue_size: 4
+
+# 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 SSD:s; not
+# necessarily on platters.
+trickle_fsync: false
+trickle_fsync_interval_in_kb: 10240
+
+# TCP port, for commands and data
+storage_port: ${entity.gossipPort?c}
+
+# SSL port, for encrypted communication.  Unused unless enabled in
+# encryption_options
+ssl_storage_port: ${entity.sslGossipPort?c}
+
+# Address 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!
+# 
+# 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 this to 0.0.0.0 is always wrong.
+listen_address: ${entity.listenAddress}
+
+# Address to broadcast to other Cassandra nodes
+# Leaving this blank will set it to the same value as listen_address
+broadcast_address: ${entity.broadcastAddress}
+
+# Whether to start the native transport server.
+# Currently, only the thrift server is started by default because the native
+# transport is considered beta.
+# 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
+native_transport_port: ${entity.nativeTransportPort?c}
+# The minimum and maximum threads for handling requests when the native
+# transport is used. The meaning is those is similar to the one of
+# rpc_min_threads and rpc_max_threads, though the default differ slightly and
+# are the ones below:
+#native_transport_min_threads: 16
+#native_transport_max_threads: 128
+
+
+# Whether to start the thrift rpc server.
+start_rpc: true
+# The address to bind the Thrift RPC service to -- clients connect
+# here. Unlike ListenAddress above, you *can* specify 0.0.0.0 here if
+# you want Thrift to listen on all interfaces.
+# 
+# Leaving this blank has the same effect it does for ListenAddress,
+# (i.e. it will be based on the configured hostname of the node).
+rpc_address: ${entity.rpcAddress}
+# port for Thrift to listen for clients on
+rpc_port: ${entity.thriftPort?c}
+
+# enable or disable keepalive on rpc connections
+rpc_keepalive: true
+
+# Cassandra provides three 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, 128KB 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).
+#
+# 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 provide 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:
+
+# Frame size for thrift (maximum field length).
+thrift_framed_transport_size_in_mb: 15
+
+# The max length of a thrift message, including all fields and
+# internal thrift overhead.
+thrift_max_message_length_in_mb: 16
+
+# 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
+
+# Add column indexes to a row after its contents reach this size.
+# Increase if your column values are large, or if you have a very large
+# number of columns.  The competing causes are, Cassandra has to
+# deserialize this much of the row to read a single column, so you want
+# it to be small - at least if you do many partial-row reads - but all
+# the index data is read for each access, so you don't want to generate
+# that wastefully either.
+column_index_size_in_kb: 64
+
+# Size limit for rows being compacted in memory.  Larger rows will spill
+# over to disk and use a slower two-pass compaction process.  A message
+# will be logged specifying the row key.
+in_memory_compaction_limit_in_mb: 64
+
+# 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 number of cores.
+# Uncomment to make compaction mono-threaded, the pre-0.8 default.
+#concurrent_compactors: 1
+
+# Multi-threaded compaction. When enabled, each compaction will use
+# up to one thread per core, plus one thread per sstable being merged.
+# This is usually only useful for SSD-based hardware: otherwise, 
+# your concern is usually to get compaction to do LESS i/o (see:
+# compaction_throughput_mb_per_sec), not more.
+multithreaded_compaction: false
+
+# 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
+
+# Track cached row keys during compaction, and re-cache their new
+# positions in the compacted sstable.  Disable if you use really large
+# key caches.
+compaction_preheat_key_cache: true
+
+# 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 400 Mbps or 50 MB/s.
+# stream_throughput_outbound_megabits_per_sec: 400
+
+# How long the coordinator should wait for read operations to complete
+read_request_timeout_in_ms: 10000
+# 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: 10000
+# 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 cassandra will assuming the request
+# was forwarded to the replica instantly by the coordinator
+#
+# 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 0, which never timeout streams.
+# streaming_socket_timeout_in_ms: 0
+
+# 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 improves cache locality
+#    when disabling read repair, which can further improve throughput.
+#    Only appropriate for single-datacenter deployments.
+#  - PropertyFileSnitch:
+#    Proximity is determined by rack and data center, which are
+#    explicitly configured in cassandra-topology.properties.
+#  - GossipingPropertyFileSnitch
+#    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.
+#  - 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 (as it did Facebook's), this is best used
+#    as an example of writing a custom Snitch class.
+#  - 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.)
+#
+# 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: ${driver.endpointSnitchName}
+
+# 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 identifer based on which to perform
+# the request scheduling. Currently the only valid option is keyspace.
+# request_scheduler_id: keyspace
+
+# index_interval controls the sampling of entries from the primrary
+# row index in terms of space versus time.  The larger the interval,
+# the smaller and less effective the sampling will be.  In technicial
+# terms, the interval coresponds to the number of index entries that
+# are skipped between taking each sample.  All the sampled entries
+# must fit in memory.  Generally, a value between 128 and 512 here
+# coupled with a large key cache size on CFs results in the best trade
+# offs.  This value is not often changed, however if you have many
+# very small rows (many to an OS page), then increasing this will
+# often lower memory usage without a impact on performance.
+index_interval: 128
+
+# 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.
+# 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]
+
+# enable or disable client/server encryption.
+client_encryption_options:
+    enabled: false
+    keystore: conf/.keystore
+    keystore_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]
+
+# 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


Mime
View raw message