使用 Silo 的解耦 HDP Spark 和 Hive

sudo pip install yq
alias kv-pairify='yq ".configuration[]" | jq ".[]" | jq -r ".name + \"=\" + .value"'

cat ${HADOOP_CONF_DIR}/core-site.xml | kv-pairify | grep "mapred"

mapred.maxthreads.generate.mapoutput=2 # Num threads to write map outputs
mapred.maxthreads.partition.closer=0 # Asynchronous map flushers
mapreduce.fileoutputcommitter.algorithm.version=2 # Use the latest committer version
mapreduce.job.reduce.slowstart.completedmaps=0.99 # 99% map, then reduce
mapreduce.reduce.shuffle.input.buffer.percent=0.9 # Min % buffer in RAM
mapreduce.reduce.shuffle.merge.percent=0.9 # Minimum % merges in RAM
mapreduce.reduce.speculative=false # Disable speculation for reducing
mapreduce.task.io.sort.factor=999 # Threshold before writing to drive
mapreduce.task.sort.spill.percent=0.9 # Minimum % before spilling to drive

cat ${HADOOP_CONF_DIR}/core-site.xml | kv-pairify | grep "s3a"

fs.s3a.access.key=minio
fs.s3a.secret.key=minio123
fs.s3a.path.style.access=true
fs.s3a.block.size=512M
fs.s3a.buffer.dir=${hadoop.tmp.dir}/s3a
fs.s3a.committer.magic.enabled=false
fs.s3a.committer.name=directory
fs.s3a.committer.staging.abort.pending.uploads=true
fs.s3a.committer.staging.conflict-mode=append
fs.s3a.committer.staging.tmp.path=/tmp/staging
fs.s3a.committer.staging.unique-filenames=true
fs.s3a.connection.establish.timeout=5000
fs.s3a.connection.ssl.enabled=false
fs.s3a.connection.timeout=200000
fs.s3a.endpoint=http://minio:9000
fs.s3a.impl=org.apache.hadoop.fs.s3a.S3AFileSystem

fs.s3a.committer.threads=2048 # Number of threads writing to MinIO
fs.s3a.connection.maximum=8192 # Maximum number of concurrent conns
fs.s3a.fast.upload.active.blocks=2048 # Number of parallel uploads
fs.s3a.fast.upload.buffer=disk # Use drive as the buffer for uploads
fs.s3a.fast.upload=true # Turn on fast upload mode
fs.s3a.max.total.tasks=2048 # Maximum number of parallel tasks
fs.s3a.multipart.size=512M # Size of each multipart chunk
fs.s3a.multipart.threshold=512M # Size before using multipart uploads
fs.s3a.socket.recv.buffer=65536 # Read socket buffer hint
fs.s3a.socket.send.buffer=65536 # Write socket buffer hint
fs.s3a.threads.max=2048 # Maximum number of threads for S3A

spark.hadoop.fs.s3a.access.key minio
spark.hadoop.fs.s3a.secret.key minio123
spark.hadoop.fs.s3a.path.style.access true
spark.hadoop.fs.s3a.block.size 512M
spark.hadoop.fs.s3a.buffer.dir ${hadoop.tmp.dir}/s3a
spark.hadoop.fs.s3a.committer.magic.enabled false
spark.hadoop.fs.s3a.committer.name directory
spark.hadoop.fs.s3a.committer.staging.abort.pending.uploads true
spark.hadoop.fs.s3a.committer.staging.conflict-mode append
spark.hadoop.fs.s3a.committer.staging.tmp.path /tmp/staging
spark.hadoop.fs.s3a.committer.staging.unique-filenames true
spark.hadoop.fs.s3a.committer.threads 2048 # number of threads writing to MinIO
spark.hadoop.fs.s3a.connection.establish.timeout 5000
spark.hadoop.fs.s3a.connection.maximum 8192 # maximum number of concurrent conns
spark.hadoop.fs.s3a.connection.ssl.enabled false
spark.hadoop.fs.s3a.connection.timeout 200000
spark.hadoop.fs.s3a.endpoint http://minio:9000
spark.hadoop.fs.s3a.fast.upload.active.blocks 2048 # number of parallel uploads
spark.hadoop.fs.s3a.fast.upload.buffer disk # use disk as the buffer for uploads
spark.hadoop.fs.s3a.fast.upload true # turn on fast upload mode
spark.hadoop.fs.s3a.impl org.apache.hadoop.spark.hadoop.fs.s3a.S3AFileSystem
spark.hadoop.fs.s3a.max.total.tasks 2048 # maximum number of parallel tasks
spark.hadoop.fs.s3a.multipart.size 512M # size of each multipart chunk
spark.hadoop.fs.s3a.multipart.threshold 512M # size before using multipart uploads
spark.hadoop.fs.s3a.socket.recv.buffer 65536 # read socket buffer hint
spark.hadoop.fs.s3a.socket.send.buffer 65536 # write socket buffer hint
spark.hadoop.fs.s3a.threads.max 2048 # maximum number of threads for S3A

hive.blobstore.use.blobstore.as.scratchdir=true
hive.exec.input.listing.max.threads=50
hive.load.dynamic.partitions.thread=25
hive.metastore.fshandler.threads=50
hive.mv.files.threads=40
mapreduce.input.fileinputformat.list-status.num-threads=50

cd /usr/hdp/current/spark2-client
su spark

./bin/spark-submit --class org.apache.spark.examples.SparkPi \
    --master yarn-client \
    --num-executors 1 \
    --driver-memory 512m \
    --executor-memory 512m \
    --executor-cores 1 \
    examples/jars/spark-examples*.jar 10

17/03/22 23:21:10 INFO DAGScheduler: Job 0 finished: reduce at SparkPi.scala:38, took 1.302805 s
Pi is roughly 3.1445191445191445

cd /usr/hdp/current/spark2-client
su spark

hadoop fs -copyFromLocal /etc/hadoop/conf/log4j.properties
          s3a://testbucket/testdata

./bin/spark-shell --master yarn-client --driver-memory 512m --executor-memory 512m

Spark context Web UI available at http://172.26.236.247:4041
Spark context available as 'sc' (master = yarn, app id = application_1490217230866_0002).
Spark session available as 'spark'.
Welcome to


      ____              __
     / __/__  ___ _____/ /__
    _\ \/ _ \/ _ `/ __/  '_/
   /___/ .__/\_,_/_/ /_/\_\   version 2.1.0.2.6.0.0-598
      /_/

Using Scala version 2.11.8 (Java HotSpot(TM) 64-Bit Server VM, Java 1.8.0_112)
Type in expressions to have them evaluated.
Type :help for more information.

scala>

scala> val file = sc.textFile("s3a://testbucket/testdata")
file: org.apache.spark.rdd.RDD[String] = s3a://testbucket/testdata MapPartitionsRDD[1] at textFile at <console>:24

scala> val counts = file.flatMap(line => line.split(" ")).map(word => (word, 1)).reduceByKey(_ + _)
counts: org.apache.spark.rdd.RDD[(String, Int)] = ShuffledRDD[4] at reduceByKey at <console>:25

scala> counts.saveAsTextFile("s3a://testbucket/wordcount")

scala> counts.count()
364

hadoop fs -ls s3a://testbucket/wordcount

Found 3 items
-rw-rw-rw-   1 spark spark          0 2019-05-04 01:36 s3a://testbucket/wordcount/_SUCCESS
-rw-rw-rw-   1 spark spark       4956 2019-05-04 01:36 s3a://testbucket/wordcount/part-00000
-rw-rw-rw-   1 spark spark       5616 2019-05-04 01:36 s3a://testbucket/wordcount/part-00001