Merge branch 'master' into SNAP-3104

# Conflicts: # cluster/src/main/scala/io/snappydata/gemxd/ClusterCallbacksImpl.scala # core/src/main/scala/io/snappydata/util/ServiceUtils.scala
TIBCOSoftware · Feb 11, 2020 · e3be0e3 · e3be0e3
2 parents dd1c9db + c312afe
commit e3be0e3
Show file tree

Hide file tree

Showing 204 changed files with 94,095 additions and 76,548 deletions.
diff --git a/LICENSE b/LICENSE
diff --git a/README.md b/README.md
@@ -102,21 +102,21 @@ SnappyData artifacts are hosted in Maven Central. You can add a Maven dependency
 ```
 groupId: io.snappydata
 artifactId: snappydata-cluster_2.11
-version: 1.1.1
+version: 1.2.0
 ```
 
 ### Using SBT Dependency
 
 If you are using SBT, add this line to your **build.sbt** for core SnappyData artifacts:
 
 ```
-libraryDependencies += "io.snappydata" % "snappydata-core_2.11" % "1.1.1"
+libraryDependencies += "io.snappydata" % "snappydata-core_2.11" % "1.2.0"
 ```
 
 For additions related to SnappyData cluster, use:
 
 ```
-libraryDependencies += "io.snappydata" % "snappydata-cluster_2.11" % "1.1.1"
+libraryDependencies += "io.snappydata" % "snappydata-cluster_2.11" % "1.2.0"
 ```
 
 You can find more specific SnappyData artifacts [here](http://mvnrepository.com/artifact/io.snappydata)

diff --git a/build.gradle b/build.gradle
@@ -72,7 +72,7 @@ allprojects {
   apply plugin: "build-time-tracker"
 
   group = 'io.snappydata'
-  version = '1.1.1'
+  version = '1.2.0'
 
   // apply compiler options
   tasks.withType(JavaCompile) {
@@ -108,7 +108,7 @@ allprojects {
     scalaBinaryVersion = '2.11'
     scalaVersion = scalaBinaryVersion + '.8'
     sparkVersion = '2.1.1'
-    snappySparkVersion = '2.1.1.7'
+    snappySparkVersion = '2.1.1.8'
     sparkDistName = "spark-${sparkVersion}-bin-hadoop2.7"
     sparkCurrentVersion = '2.3.2'
     sparkCurrentDistName = "spark-${sparkCurrentVersion}-bin-hadoop2.7"
@@ -117,6 +117,10 @@ allprojects {
     junitVersion = '4.12'
     mockitoVersion = '1.10.19'
     hadoopVersion = '2.7.7'
+    gcsHadoop2ConnectorVersion = 'hadoop2-2.0.0'
+    gcsHadoop3ConnectorVersion = 'hadoop3-2.0.0'
+    sparkAvroVersion = '4.0.0'
+    sparkXmlVersion = '0.4.1'
     scalatestVersion = '2.2.6'
     jettyVersion = '9.2.26.v20180806'
     guavaVersion = '14.0.1'
@@ -151,7 +155,7 @@ allprojects {
     antlr2Version = '2.7.7'
 
     pegdownVersion = '1.6.0'
-    snappyStoreVersion = '1.6.4'
+    snappyStoreVersion = '1.6.5'
     snappydataVersion = version
     pulseVersion = '1.5.1'
     zeppelinInterpreterVersion = '0.7.3.6'
@@ -163,12 +167,20 @@ allprojects {
     osFamilyName = osName.getFamilyName().replace(' ', '').toLowerCase()
     osVersion = System.getProperty('os.version')
     buildDate = new Date().format('yyyy-MM-dd HH:mm:ss Z')
+    buildDateShort = ''
+    if (rootProject.hasProperty('withDate')) {
+      buildDateShort = "${new Date().format('yyyyMMdd')}_"
+    }
+    devEdition = ''
+    if (rootProject.hasProperty('dev')) {
+      devEdition = "-dev"
+    }
     buildNumber = new Date().format('MMddyy')
     jdkVersion = System.getProperty('java.version')
-    sparkJobServerVersion = '0.6.2.10'
+    sparkJobServerVersion = '0.6.2.11'
     eclipseCollectionsVersion = '9.2.0'
     fastutilVersion = '8.2.2'
-    sparkMetricsLibVersion = '2.0.0'
+    snappySparkMetricsLibVersion = '2.0.0.1'
 
     gitCmd = "git --git-dir=${rootDir}/.git --work-tree=${rootDir}"
     gitBranch = "${gitCmd} rev-parse --abbrev-ref HEAD".execute().text.trim()
@@ -568,7 +580,7 @@ subprojects {
 
   // apply default manifest
   if (rootProject.hasProperty('enablePublish')) {
-    createdBy = 'TIBCO Software Inc.'
+    createdBy = vendorName
   }
   jar {
     manifest {
@@ -914,6 +926,7 @@ task product(type: Zip) {
   dependsOn ":snappy-spark:snappy-spark-assembly_${scalaBinaryVersion}:sparkProduct"
   dependsOn ':snappy-launcher:jar'
   dependsOn ':jdbcJar'
+  dependsOn ':copyShadowJars'
 
   def clusterProject = project(":snappy-cluster_${scalaBinaryVersion}")
   def launcherProject = project(':snappy-launcher')
@@ -1074,6 +1087,11 @@ task product(type: Zip) {
           into "${snappyProductDir}/connectors"
           include "*.jar"
         }
+        copy {
+          from "${jdbcConnectorProject.projectDir}/../tdv-connector/lib"
+          into "${snappyProductDir}/connectors"
+          include "csjdbc8.jar"
+        }
       }
       if (hasGemFireConnectorProject) {
         copy {
@@ -1200,7 +1218,6 @@ ospackage {
 }
 
 buildRpm {
-  dependsOn ':packageVSD'
   if (rootProject.hasProperty('enablePublish')) {
     dependsOn ':packageZeppelinInterpreter'
   }
@@ -1216,7 +1233,6 @@ buildRpm {
 }
 
 buildDeb {
-  dependsOn ':packageVSD'
   if (rootProject.hasProperty('enablePublish')) {
     dependsOn ':packageZeppelinInterpreter'
   }
@@ -1235,13 +1251,11 @@ buildDeb {
 distTar {
   // archiveName = 'TIB_compute-ce_' + version + '_' + osFamilyName + '.tar.gz'
   if (isEnterpriseProduct) {
-    archiveName = 'TIB_compute_' + version + '_' + osFamilyName + '.tar.gz'
+    archiveName = 'TIB_compute' + devEdition + '_' + version + '_' + buildDateShort + osFamilyName + '.tar.gz'
   } else {
     classifier 'bin'
   }
   dependsOn product
-  // also package VSD
-  dependsOn ':packageVSD'
   if (rootProject.hasProperty('enablePublish')) {
     dependsOn ':packageZeppelinInterpreter'
   }
@@ -1255,13 +1269,11 @@ distTar {
 distZip {
   // archiveName = 'TIB_compute-ce_' + version + '_' + osFamilyName + '.zip'
   if (isEnterpriseProduct) {
-    archiveName = 'TIB_compute_' + version + '_' + osFamilyName + '.zip'
+    archiveName = 'TIB_compute' + devEdition + '_' + version + '_' + buildDateShort + osFamilyName + '.zip'
   } else {
     classifier 'bin'
   }
   dependsOn product
-  // also package VSD
-  dependsOn ':packageVSD'
   if (rootProject.hasProperty('enablePublish')) {
     dependsOn ':packageZeppelinInterpreter'
   }
@@ -1332,7 +1344,6 @@ task distInstallers {
 task distProduct {
   dependsOn product, distTar, distZip
   dependsOn distInstallers
-  dependsOn copyShadowJars
 }
 
 task generateSources {
@@ -1372,6 +1383,7 @@ task buildAll {
   dependsOn getTasksByName('assemble', true).collect { it.path }
   dependsOn getTasksByName('product', true).collect { it.path }
   dependsOn getTasksByName('testClasses', true).collect { it.path }
+  dependsOn copyShadowJars
   mustRunAfter cleanAll
 }
 task buildDtests {
@@ -1386,7 +1398,9 @@ task checkAll {
   if (rootProject.hasProperty('spark')) {
     dependsOn ':snappy-spark:check'
   }
-  dependsOn ":snappy-cluster_${scalaBinaryVersion}:check"
+  if (!rootProject.hasProperty('cluster.skip')) {
+    dependsOn ":snappy-cluster_${scalaBinaryVersion}:check"
+  }
   dependsOn ":snappy-examples_${scalaBinaryVersion}:check"
   if (!rootProject.hasProperty('aqp.skip') && hasAqpProject && isEnterpriseProduct) {
     dependsOn ":snappy-aqp_${scalaBinaryVersion}:check"
@@ -1489,37 +1503,11 @@ task packagePulse { doLast {
   }
 } }
 
-task packageVSD { doLast {
-  String thirdparty = System.env.THIRDPARTYDIR
-  String vsdDir = ''
-
-  if (thirdparty == null || thirdparty.length() == 0) {
-    vsdDir = "${projectDir}/../thirdparty/vsd"
-  } else {
-    vsdDir = "${thirdparty}/vsd"
-  }
-
-  String vsdDistDir = "${vsdDir}/70/vsd"
-  if (file(vsdDistDir).canWrite()) {
-    println ''
-    println "Copying VSD from ${vsdDistDir} to ${snappyProductDir}/vsd"
-    println ''
-    delete "${snappyProductDir}/vsd"
-    copy {
-      from vsdDistDir
-      into "${snappyProductDir}/vsd"
-    }
-  } else {
-    println "Skipping VSD due to unwritable ${vsdDistDir}"
-  }
-} }
-
 task sparkPackage {
   dependsOn ":snappy-core_${scalaBinaryVersion}:sparkPackage"
 }
 
 packagePulse.mustRunAfter product
-packageVSD.mustRunAfter product
 packageZeppelinInterpreter.mustRunAfter product
 
 distTar.mustRunAfter clean, cleanAll, product

diff --git a/cluster/bin/snappy b/cluster/bin/snappy
@@ -76,9 +76,10 @@ elif [ -z "$SNAPPY_NO_QUICK_LAUNCH" -a $# -ge 2 \
   . "${SPARK_HOME}"/bin/load-snappy-env.sh
 
   HOSTNAME_FOR_CLIENTS=
+  IMPLICIT_AWS_CLIENT_BIND_ADDRESS=
   if [ "$2" = "start" ]; then
     # set hostname-for-clients and SPARK_PUBLIC_DNS in AWS (only supported for Linux)
-    if [ -z "$SPARK_PUBLIC_DNS" ]; then
+    if [ -z "$SPARK_PUBLIC_DNS" -o -n "$IMPLICIT_CLIENT_BIND_ADDRESS" ]; then
       CHECK_AWS=1
       if [ -r /sys/hypervisor/uuid ]; then
         if ! grep -q '^ec2' /sys/hypervisor/uuid; then
@@ -93,19 +94,27 @@ elif [ -z "$SNAPPY_NO_QUICK_LAUNCH" -a $# -ge 2 \
         CHECK_AWS=
       fi
       if [ -n "$CHECK_AWS" ]; then
-        SPARK_PUBLIC_DNS="$(curl -s --connect-timeout 3 http://169.254.169.254/latest/meta-data/public-ipv4 | head -1)"
-        if [ -n "$SPARK_PUBLIC_DNS" ]; then
-          if ! echo $"${@// /\\ }" | grep -q 'hostname-for-clients='; then
-            HOSTNAME_FOR_CLIENTS="-hostname-for-clients=$SPARK_PUBLIC_DNS"
+        if [ -z "$SPARK_PUBLIC_DNS" ]; then
+          SPARK_PUBLIC_DNS="$(curl -s --connect-timeout 3 http://169.254.169.254/latest/meta-data/public-ipv4 | head -1)"
+          if [ -n "$SPARK_PUBLIC_DNS" ]; then
+            if ! echo $"${@// /\\ }" | grep -q 'hostname-for-clients='; then
+              HOSTNAME_FOR_CLIENTS="-hostname-for-clients=$SPARK_PUBLIC_DNS"
+            fi
+            export SPARK_PUBLIC_DNS
           fi
-          export SPARK_PUBLIC_DNS
         fi
+        if [ -n "$IMPLICIT_CLIENT_BIND_ADDRESS" ]; then
+          IMPLICIT_AWS_CLIENT_BIND_ADDRESS="-client-bind-address=0.0.0.0"
+        fi
+      elif [ -n "$IMPLICIT_CLIENT_BIND_ADDRESS" ]; then
+        IMPLICIT_AWS_CLIENT_BIND_ADDRESS="-client-bind-address=${IMPLICIT_CLIENT_BIND_ADDRESS}"
       fi
     fi
   fi
 
   JARS="`echo "${SPARK_HOME}"/jars/snappydata-launcher* "${SPARK_HOME}"/jars/gemfire-shared* "${SPARK_HOME}"/jars/jna-4.* | sed 's/ /:/g'`"
-  exec $RUNNER $JAVA_ARGS -Xverify:none -cp "$JARS" io.snappydata.tools.QuickLauncher "$@" $HOSTNAME_FOR_CLIENTS
+  exec $RUNNER $JAVA_ARGS -Xverify:none -cp "$JARS" io.snappydata.tools.QuickLauncher "$@" $HOSTNAME_FOR_CLIENTS $IMPLICIT_AWS_CLIENT_BIND_ADDRESS
+  IMPLICIT_CLIENT_BIND_ADDRESS=
 else
   # use full snappy launcher
   exec "$SPARK_HOME"/bin/spark-class $JAVA_ARGS io.snappydata.tools.SnappyUtilLauncher "$@"

diff --git a/cluster/bin/snappy-scala b/cluster/bin/snappy-scala
@@ -0,0 +1,26 @@
+#!/usr/bin/env bash
+
+#
+# Copyright (c) 2017-2019 TIBCO Software Inc. All rights reserved.
+#
+# Licensed 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. See accompanying
+# LICENSE file.
+#
+
+function absPath() {
+  perl -MCwd -le 'print Cwd::abs_path(shift)' "$1"
+}
+bin="$(dirname "$(absPath "$0")")"
+
+export SNAPPY_SCRIPT_NAME=snappy-scala
+exec "$bin/snappy" "$@"
diff --git a/cluster/build.gradle b/cluster/build.gradle
@@ -133,6 +133,39 @@ dependencies {
     exclude(group: 'org.apache.directory.server', module: 'apacheds-kerberos-codec')
   }
 
+  compile "io.snappydata:spark-metrics:${snappySparkMetricsLibVersion}"
+
+  compile (group: 'com.databricks', name:'spark-xml_2.11', version: sparkXmlVersion) {
+    //exclude(group: 'org.scala-lang', module: 'scala-library')
+  }
+  compile (group: 'com.databricks', name:'spark-avro_2.11', version: sparkAvroVersion) {
+    //exclude(group: 'org.scala-lang', module: 'scala-library')
+    //exclude(group: 'org.apache.avro', module: 'avro')
+  }
+  compile(group:'com.google.cloud.bigdataoss', name:'gcs-connector', version: gcsHadoop2ConnectorVersion, classifier: 'shaded')
+
+  compile(group: 'org.apache.hadoop', name: 'hadoop-azure', version: hadoopVersion) {
+    // exclude some dependencies like in hadoop-aws to avoid conflicts with other deps
+    exclude(group: 'asm', module: 'asm')
+    exclude(group: 'org.codehaus.jackson', module: 'jackson-mapper-asl')
+    exclude(group: 'org.ow2.asm', module: 'asm')
+    exclude(group: 'org.apache.zookeeper', module: 'zookeeper')
+    exclude(group: 'org.jboss.netty', module: 'netty')
+    exclude(group: 'jline', module: 'jline')
+    exclude(group: 'commons-logging', module: 'commons-logging')
+    exclude(group: 'org.mockito', module: 'mockito-all')
+    exclude(group: 'org.mortbay.jetty', module: 'servlet-api-2.5')
+    exclude(group: 'javax.servlet', module: 'servlet-api')
+    exclude(group: 'junit', module: 'junit')
+    exclude(group: 'com.google.guava', module: 'guava')
+    exclude(group: 'com.sun.jersey')
+    exclude(group: 'com.sun.jersey.jersey-test-framework')
+    exclude(group: 'com.sun.jersey.contribs')
+    exclude(group: 'com.google.protobuf', module: 'protobuf-java')
+    exclude(group: 'com.jcraft', module: 'jsch')
+    exclude(group: 'org.apache.directory.server', module: 'apacheds-kerberos-codec')
+}
+
   testCompile project(':dunit')
   testCompile "it.unimi.dsi:fastutil:${fastutilVersion}"
   testCompile "org.scalatest:scalatest_${scalaBinaryVersion}:${scalatestVersion}"

diff --git a/cluster/conf/leads.template b/cluster/conf/leads.template
@@ -37,7 +37,7 @@
 #
 # IV) Start the SnappyData Zeppelin interpreter on the Lead node
 #
-#     lead1   -dir=/tmp/data/server -spark.ui.port=3333 -spark.executor.cores=16 -zeppelin.interpreter.enable=true -classpath=<Path to jar of Zeppelin Interpreter for SnappyData>
+#     lead1   -dir=/tmp/data/server -spark.ui.port=3333 -spark.executor.cores=16 -zeppelin.interpreter.enable=true
 #
 # For more options, see http://snappydatainc.github.io/snappydata/configuration/#configuration
 localhost
diff --git a/cluster/conf/locators.template b/cluster/conf/locators.template
@@ -52,6 +52,9 @@
 #
 #     <private hostname/IP> -client-bind-address=<private hostname/IP> -hostname-for-clients=<public hostname/IP for clients>
 #
+# NOTE: For AWS environment, the cluster launch script (snappy-start-all.sh) automatically appends above two properties with
+# appropriate values to the locator's configuration, so that users do not have to specify them here explicitly.
+#
 # III) Logging to different directory 
 # Specify the startup directory where the logs and configuration files for that locator instance
 # are managed. 

diff --git a/cluster/conf/servers.template b/cluster/conf/servers.template
@@ -39,6 +39,10 @@
 #
 #     <private hostname/IP> -client-bind-address=<private hostname/IP> -client-port=1555 -hostname-for-clients=<public hostname/IP for clients>
 # 
+# NOTE: For AWS environment, the cluster launch script (snappy-start-all.sh) automatically appends above two properties
+# viz. -client-bind-address and -hostname-for-clients with appropriate values to the server's configuration, so that
+# users do not have to specify them here explicitly.
+#
 # For more configuration options,
 # see http://snappydatainc.github.io/snappydata/configuration/#configuration
 localhost
diff --git a/cluster/sbin/snappy-nodes.sh b/cluster/sbin/snappy-nodes.sh
@@ -201,8 +201,8 @@ function execute() {
 
     # set the default client-bind-address and locator's peer-discovery-address
     if [ -z "${clientBindAddress}" -a "${componentType}" != "lead" ]; then
-      args="${args} -client-bind-address=${host}"
-      clientBindAddress="${host}"
+      preCommand="${preCommand}export IMPLICIT_CLIENT_BIND_ADDRESS=$host; "
+      export IMPLICIT_CLIENT_BIND_ADDRESS="${host}"
     fi
     if [ -z "$(echo $args $"${@// /\\ }" | grep 'peer-discovery-address=')" -a "${componentType}" = "locator" ]; then
       args="${args} -peer-discovery-address=${host}"
@@ -243,7 +243,11 @@ function execute() {
       -*) postArgs="$postArgs $arg"
     esac
   done
-  if [ "$host" != "localhost" ]; then
+  THIS_HOST_IP=
+  if [ "$(echo `uname -s`)" == "Linux" ]; then
+    THIS_HOST_IP="$(echo `hostname -I` | grep "$host")"
+  fi
+  if [ "$host" != "localhost" -a -z "$THIS_HOST_IP" ]; then
     if [ "$dirfolder" != "" ]; then
       # Create the directory for the snappy component if the folder is a default folder
       (ssh $SPARK_SSH_OPTS "$host" \