Spark Optimization

Driver Program
    ↓
Job (triggered by action)
    ↓
Stages (separated by shuffles)
    ↓
Tasks (one per partition)

from pyspark.sql import SparkSession
from pyspark.sql import functions as F

# Create optimized Spark session
spark = (SparkSession.builder
    .appName("OptimizedJob")
    .config("spark.sql.adaptive.enabled", "true")
    .config("spark.sql.adaptive.coalescePartitions.enabled", "true")
    .config("spark.sql.adaptive.skewJoin.enabled", "true")
    .config("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
    .config("spark.sql.shuffle.partitions", "200")
    .getOrCreate())

# Read with optimized settings
df = (spark.read
    .format("parquet")
    .option("mergeSchema", "false")
    .load("s3://bucket/data/"))

# Efficient transformations
result = (df
    .filter(F.col("date") >= "2024-01-01")
    .select("id", "amount", "category")
    .groupBy("category")
    .agg(F.sum("amount").alias("total")))

result.write.mode("overwrite").parquet("s3://bucket/output/")

# Calculate optimal partition count
def calculate_partitions(data_size_gb: float, partition_size_mb: int = 128) -> int:
    """
    Optimal partition size: 128MB - 256MB
    Too few: Under-utilization, memory pressure
    Too many: Task scheduling overhead
    """
    return max(int(data_size_gb * 1024 / partition_size_mb), 1)

# Repartition for even distribution
df_repartitioned = df.repartition(200, "partition_key")

# Coalesce to reduce partitions (no shuffle)
df_coalesced = df.coalesce(100)

# Partition pruning with predicate pushdown
df = (spark.read.parquet("s3://bucket/data/")
    .filter(F.col("date") == "2024-01-01"))  # Spark pushes this down

# Write with partitioning for future queries
(df.write
    .partitionBy("year", "month", "day")
    .mode("overwrite")
    .parquet("s3://bucket/partitioned_output/"))

from pyspark.sql import functions as F
from pyspark.sql.types import *

# 1. Broadcast Join - Small table joins
# Best when: One side < 10MB (configurable)
small_df = spark.read.parquet("s3://bucket/small_table/")  # < 10MB
large_df = spark.read.parquet("s3://bucket/large_table/")  # TBs

# Explicit broadcast hint
result = large_df.join(
    F.broadcast(small_df),
    on="key",
    how="left"
)

# 2. Sort-Merge Join - Default for large tables
# Requires shuffle, but handles any size
result = large_df1.join(large_df2, on="key", how="inner")

# 3. Bucket Join - Pre-sorted, no shuffle at join time
# Write bucketed tables
(df.write
    .bucketBy(200, "customer_id")
    .sortBy("customer_id")
    .mode("ove