Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

SNAP 2710 - Updating code to use structured streaming #17

Open
wants to merge 30 commits into
base: master
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from 22 commits
Commits
Show all changes
30 commits
Select commit Hold shift + click to select a range
993094b
Removing memsql, cassandra, rabitmq modules.
Oct 17, 2019
44e94e4
- SnappyAPILogAggregator class contains the structured streaming job for
Oct 22, 2019
a341625
[SNAP-3195] Exposing `spark.sql.constraintPropagation.enabled` config
Oct 22, 2019
4c6fc3d
Including some compileOnly dependencies as part of test dependencies.
Nov 4, 2019
614c6ce
- Eliminating the use of threadlocal to reuse instances while doing AVRO
Nov 4, 2019
50e679a
Updating README file.
Nov 4, 2019
a0da528
Fixing serializer name
Nov 4, 2019
ca36c75
Using structured streaming windowed aggregation with watermarking
Dec 5, 2019
2322df4
Formatting and correcting README
Dec 10, 2019
0ca98cf
Cleaning up some unused code. Completing some TODOs.
Dec 13, 2019
058c3d3
Removed some TODOs along with minor documentation corrections
Dec 16, 2019
aba2792
Clean up
Dec 16, 2019
20db11a
some corrections
Dec 16, 2019
25c7024
Increasing max offset value per trigger.
Dec 18, 2019
2bb9391
Creating sample table on top of target table.
Dec 19, 2019
bfd1547
Dropping sample table before base table.
Dec 20, 2019
1b300ce
Adding docs in the code.
Jan 6, 2020
c1d4c51
Updating copyright header
Jan 13, 2020
137e0a5
removing unused maven repos
Jan 17, 2020
8146081
Updating copyright header
Feb 13, 2020
7ea61b0
- updating diagram
Feb 17, 2020
9ef4121
Keeping default number of producer threads to 1
Feb 17, 2020
b0b807d
incorporating review comments
Feb 24, 2020
e70ecc6
incorporating review comments
Feb 24, 2020
1bb8f8a
Adding note declaring AQP related instructions enterprise only.
Feb 24, 2020
ce23b64
Adding license file
Mar 2, 2020
4f77b94
Updating copyright headers
Mar 2, 2020
e28e664
Some corrections in README
Mar 12, 2020
2896620
- Changing artifact name to `snappy-examples` from `snappy-poc`
Mar 12, 2020
39cbc19
Setting watermark delayThreshold to 0 seconds to make sure that the
Mar 16, 2020
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file modified AdAnalytics_Architecture.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
349 changes: 195 additions & 154 deletions README.md

Large diffs are not rendered by default.

3 changes: 0 additions & 3 deletions assembly/build.gradle
Original file line number Diff line number Diff line change
Expand Up @@ -4,9 +4,6 @@ archivesBaseName = 'snappy-poc'

dependencies {
compile rootProject
compile project(':spark-memsql')
compile project(':spark-cassandra')
compile project(':rabbitmq-snappy')
}

shadowJar {
Expand Down
112 changes: 13 additions & 99 deletions build.gradle
Original file line number Diff line number Diff line change
Expand Up @@ -8,16 +8,11 @@ archivesBaseName = 'snappy-poc'

allprojects {

version = '1.0.0'
version = '1.2.0'

repositories {
mavenLocal()
mavenCentral()
maven { url "https://oss.sonatype.org/content/groups/public" }
maven { url "https://oss.sonatype.org/content/repositories/snapshots" }
maven { url "http://repository.snappydata.io/repository/internal" }
maven { url "http://repository.snappydata.io/repository/snapshots" }
maven { url "http://mvnrepository.com/artifact" }
maven { url 'https://clojars.org/repo' }
}

apply plugin: 'java'
Expand All @@ -28,8 +23,8 @@ allprojects {
apply plugin: "com.commercehub.gradle.plugin.avro"

ext {
sparkVersion = '2.0.1-3'
snappyVersion = '1.0.0'
sparkVersion = '2.1.1.8'
snappyVersion = '1.2.0'
}

configurations.all {
Expand All @@ -49,14 +44,14 @@ dependencies {
compileOnly "io.snappydata:snappy-spark-core_2.11:${sparkVersion}"
compileOnly "io.snappydata:snappy-spark-catalyst_2.11:${sparkVersion}"
compileOnly "io.snappydata:snappy-spark-sql_2.11:${sparkVersion}"
// compileOnly "io.snappydata:snappydata-aqp_2.11:${snappyVersion}"

compile 'com.miguno:kafka-avro-codec_2.10:0.1.1-SNAPSHOT'
compile 'org.apache.kafka:kafka_2.11:0.8.2.1'
compile 'com.twitter:algebird-core_2.10:0.1.11'
compile 'com.googlecode.javaewah:JavaEWAH:1.1.5'
compile 'org.joda:joda-convert:1.2'
compile 'com.opencsv:opencsv:3.3'

compile 'org.apache.kafka:kafka-clients:0.10.0.1'
compile 'org.apache.kafka:kafka_2.11:0.10.0.1'
}

sourceSets {
test.compileClasspath += configurations.compileOnly
test.runtimeClasspath += configurations.compileOnly
}

task generateAvro(type: com.commercehub.gradle.plugin.avro.GenerateAvroJavaTask) {
Expand All @@ -68,7 +63,6 @@ compileJava.source(generateAvro.outputs)

avro.stringType = "charSequence"


ext {
assemblyJar = rootProject.tasks.getByPath(':assembly:shadowJar').outputs
}
Expand All @@ -79,84 +73,4 @@ task generateAdImpressions(type: JavaExec, dependsOn: classes) {
main = 'io.snappydata.adanalytics.KafkaAdImpressionProducer'
classpath sourceSets.test.runtimeClasspath
environment 'PROJECT_ASSEMBLY_JAR', assemblyJar.files.asPath
}

task aggeregateAdImpressions_API(type: JavaExec, dependsOn: classes) {
main = 'io.snappydata.adanalytics.SnappyAPILogAggregator'
jvmArgs = ['-XX:MaxPermSize=512m']
classpath sourceSets.test.runtimeClasspath
environment 'PROJECT_ASSEMBLY_JAR', assemblyJar.files.asPath
}

task aggeregateAdImpressions_SQL(type: JavaExec, dependsOn: classes) {
main = 'io.snappydata.adanalytics.SnappySQLLogAggregator'
jvmArgs = ['-XX:MaxPermSize=512m']
classpath sourceSets.test.runtimeClasspath
environment 'PROJECT_ASSEMBLY_JAR', assemblyJar.files.asPath
}

task generateAdImpressions_Socket(type: JavaExec, dependsOn: classes) {
main = 'io.snappydata.benchmark.SocketAdImpressionGenerator'
classpath sourceSets.test.runtimeClasspath
environment 'PROJECT_ASSEMBLY_JAR', assemblyJar.files.asPath
maxHeapSize = "8196m"
}

task startSnappyIngestionPerf_Socket(type: JavaExec, dependsOn: classes) {
main = 'io.snappydata.benchmark.SocketSnappyIngestionPerf'
jvmArgs = ['-XX:MaxPermSize=512m']
maxHeapSize = "8196m"
classpath sourceSets.test.runtimeClasspath
environment 'PROJECT_ASSEMBLY_JAR', assemblyJar.files.asPath
}

task startSnappyIngestionPerf_CustomReceiver(type: JavaExec, dependsOn: classes) {
main = 'io.snappydata.benchmark.CustomReceiverSnappyIngestionPerf'
jvmArgs = ['-XX:MaxPermSize=512m']
maxHeapSize = "8196m"
classpath sourceSets.test.runtimeClasspath
environment 'PROJECT_ASSEMBLY_JAR', assemblyJar.files.asPath
}

task startSnappyIngestionPerf_CSV(type: JavaExec, dependsOn: classes) {
main = 'io.snappydata.benchmark.CSVSnappyIngestionPerf'
jvmArgs = ['-XX:MaxPermSize=512m']
maxHeapSize = "8196m"
classpath sourceSets.test.runtimeClasspath
environment 'PROJECT_ASSEMBLY_JAR', assemblyJar.files.asPath
}

task startSnappyIngestionPerf_Kafka(type: JavaExec, dependsOn: classes) {
main = 'io.snappydata.benchmark.KafkaSnappyIngestionPerf'
jvmArgs = ['-XX:MaxPermSize=512m']
maxHeapSize = "8196m"
classpath sourceSets.test.runtimeClasspath
environment 'PROJECT_ASSEMBLY_JAR', assemblyJar.files.asPath
}

task product(type: Exec) {
dependsOn ':assembly:shadowJar'

def productDir = "${rootProject.buildDir}/snappydata-poc"
def snappyData = System.env.SNAPPYDATA
if (snappyData == null || snappyData.length() == 0) {
snappyData = "${projectDir}/../snappydata"
}

doFirst {
delete productDir
file("${productDir}/lib").mkdirs()
}

// first execute the snappydata "product" target based on env var SNAPPYDATA
workingDir snappyData
commandLine './gradlew', 'copyProduct', "-PcopyToDir=${productDir}"

// lastly copy own assembly fat jar in product lib dir
doLast {
copy {
from assemblyJar
into "${productDir}/lib"
}
}
}
}
23 changes: 0 additions & 23 deletions rabbitmq-snappy/build.gradle

This file was deleted.

This file was deleted.

This file was deleted.

This file was deleted.

2 changes: 1 addition & 1 deletion settings.gradle
Original file line number Diff line number Diff line change
@@ -1 +1 @@
include 'spark-memsql', 'spark-cassandra', 'rabbitmq-snappy', 'assembly'
include 'assembly'
37 changes: 0 additions & 37 deletions spark-cassandra/build.gradle

This file was deleted.

Loading