From 2139f983fbe71bf6411259e8ddb460a79663dcb8 Mon Sep 17 00:00:00 2001 From: earrage Date: Mon, 22 Oct 2018 13:53:54 -0700 Subject: Initial commit for Spark to analyze visibility data - Add Apache Spark 2.3 with native Kubernetes support. - Runs self contained within K8s cluster in clover-system namespace. One container (clover-spark) includes Clover Spark JAR artifact. This container interacts with the K8s API to spawn a spark-driver pod. This pod in turn spawns executor pods to execute Spark jobs. - Currently JAR is included in source for convenience and must be built with sbt (install sbt and execute sbt package) - Includes JAR from DataStax to provide Cassandra connector to analyze Cassandra schemas as RDDs (Resilient Distributed Dataset). - Includes Redis interface JAR to write analyzed data back to visibility (UI, CLI or API). - Second container (clover-spark-submit) submits Spark jobs continuously to allow Spark to be operated entirely within the cluster. - Two Spark jobs (CloverSlow, CloverFast) allows some analytics to be provided in real-time and other analytics to be provided over longer horizons. - Each Spark job spawns two executor pods. - Includes yaml manifest to deploy clover-spark-submit with the necessary RBAC permissions to interact with the K8s API. - Data analyzed includes tracing and metrics schemas obtained by clover-collector and written to Cassandra. - Docker builds of clover-spark and clover-spark-submit are provided and will be pushed as OPNFV DockerHub images in a separate patch. Change-Id: I2e92c41fd75d4ebba948c0f8cb60face57005e50 Signed-off-by: earrage --- clover/spark/src/main/scala/CloverFast.scala | 55 ++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) create mode 100644 clover/spark/src/main/scala/CloverFast.scala (limited to 'clover/spark/src/main/scala/CloverFast.scala') diff --git a/clover/spark/src/main/scala/CloverFast.scala b/clover/spark/src/main/scala/CloverFast.scala new file mode 100644 index 0000000..b746760 --- /dev/null +++ b/clover/spark/src/main/scala/CloverFast.scala @@ -0,0 +1,55 @@ +// Copyright (c) Authors of Clover +// +// All rights reserved. This program and the accompanying materials +// are made available under the terms of the Apache License, Version 2.0 +// which accompanies this distribution, and is available at +// http://www.apache.org/licenses/LICENSE-2.0 + +import org.apache.spark.sql.SparkSession +import com.datastax.spark.connector._ +import org.apache.spark.sql.cassandra._ +import org.apache.spark.SparkContext +import org.apache.spark.SparkConf + +import com.redis._ + +object CloverFast { + def main(args: Array[String]) { + val sp = SparkSession.builder.appName("Clover Fast") + .getOrCreate() + sp.stop() + + val CassandraConnect = "cassandra.clover-system" + val RedisConnect = "redis.default" + + // Cassandra, Redis, Spark Context + val scch = "spark.cassandra.connection.host" + val conf = new SparkConf(true).set(scch, CassandraConnect) + val redis = new RedisClient(RedisConnect, 6379) + val sc = new SparkContext(conf) + + for( x <- 1 to 10000 ) { + + try { + val spans = sc.cassandraTable("visibility", "spans") + .select("spanid").cassandraCount() + redis.set("span_count", spans) + + val traces = sc.cassandraTable("visibility", "traces") + .select("traceid").cassandraCount() + redis.set("trace_count", traces) + + val metrics = sc.cassandraTable("visibility", "metrics") + .select("monitor_time").cassandraCount() + redis.set("metric_count", metrics) + + } + catch { + case unknown : Throwable => println("System counts exception: " + + unknown) + } + + } + + } +} -- cgit 1.2.3-korg