Spark Job Scripts

back to the Spark page

spark-local-cluster.sh

#!/bin/bash
#filename: spark-local-cluster.sh

#SBATCH --job-name=spark_cluster
#SBATCH --nodes=1 # nodes allocated to the job
#SBATCH --cpus-per-task=16 # the number of CPUs allocated per task
#SBATCH --exclusive # not sharing of allocated nodes with other running jobs
#SBATCH --time=03:00:00
#SBATCH --output=spark_cluster.log
#SBATCH --error=spark_cluster.err

###SBATCH --ntasks= # tasks to be created for the job
###SBATCH --ntasks-per-core= # max number of tasks per allocated core
###SBATCH --ntasks-per-node= # max number of tasks per allocated node
###SBATCH --mail-type=END,FAIL
###SBATCH --mail-user=<yourID>@ufl.edu

module load spark
### Set Spark variables
export SPARK_LOCAL_DIRS=$HOME/spark/tmp
export SPARK_WORKER_DIR=$SPARK_LOCAL_DIRS
export SPARK_WORKER_CORES=$SLURM_CPUS_PER_TASK
export SPARK_MASTER_PORT=7077
export SPARK_MASTER_WEBUI_PORT=8080
export SPARK_NO_DAEMONIZE=true
export SPARK_LOG_DIR=$SPARK_LOCAL_DIRS
#export SPARK_CONF_DIR=$SPARK_LOCAL_DIRS
mkdir -p $SPARK_LOCAL_DIRS

MASTER_HOST=$(scontrol show hostname $SLURM_NODELIST | head -n 1)
export SPARK_MASTER_NODE=$(host $MASTER_HOST | head -1 | cut -d ' ' -f 4)
export MAX_SLAVES=$(expr $SLURM_JOB_NUM_NODES - 1)

# start master
$SPARK_HOME/sbin/start-master.sh &

# start workers
# use spark defaults for worker resources (all mem -1 GB, all cores) since using exclusive

$SPARK_HOME/sbin/start-slave.sh spark://$SPARK_MASTER_NODE:$SPARK_MASTER_PORT

pi_with_pythonstartup.py

from operator import add
from random import random

partitions =10
n = 100000 * partitions

def f(_):
    x = random() * 2 - 1
    y = random() * 2 - 1
    return 1 if x ** 2 + y ** 2 <= 1 else 0

count = sc.parallelize(range(1, n + 1), partitions).map(f).reduce(add)
print("Pi is roughly %f" % (4.0 * count / n))