December 2019 – Large-Scale Data Engineering in Cloud

Amazon, AWS, Hive, I/O, Parquet, S3, Spark

Spark – Slow Load Into Partitioned Hive Table on S3 – Direct Writes, Output Committer Algorithms

December 30, 2019

I have a Spark job that transforms incoming data from compressed text files into Parquet format and loads them into a daily partition of a Hive table. This is a typical job in a data lake, it is quite simple but in my case it was very slow.

Initially it took about 4 hours to convert ~2,100 input .gz files (~1.9 TB of data) into Parquet, while the actual Spark job took just 38 minutes to run and the remaining time was spent on loading data into a Hive partition.

Let’s see what is the reason of such behavior and how we can improve the performance.

Read More

dmtolpeko
Hive, Memory, Tez, YARN

Hive – Issues With Large YARN Containers – Low Concurrency and Utilization, High Execution Time

December 11, 2019

I was asked to tune a Hive query that ran more than 10 hours. It was running on a 100 node cluster with 16 GB available for YARN containers on each node.

Although the query processed about 2 TB of input data, it did a fairly simple aggregation on user_id column and did not look too complex. It had 1 Map stage with 1,500 tasks and 1 Reduce stage with 7,000 tasks.

All map tasks completed within 30 minutes, and the query stuck on the Reduce phase. So what was wrong?

Read More

dmtolpeko
Auto Scaling, Presto

Presto – Query Auto Scaling Limitations – Low Utilization After Upscale – GROUP BY Partitioned Stage, query-manager.required-workers

December 4, 2019

One of the powerful features of Presto is auto scaling of compute resources for already running queries. When a cluster is idle you can reduce its size or even terminate the cluster, and then dynamically add nodes when necessary depending on the compute requirements of queries.

Unfortunately, there are some limitations since not all stages can scale on the fly, so you have to use some workarounds to have reasonable cold start performance.

Read More

dmtolpeko
ETL, Hive, Presto

Presto vs Hive – SLA Risks for Long Running ETL – Failures and Retries Due to Node Loss

December 4, 2019

Presto is an extremely powerful distributed SQL query engine, so at some point you may consider using it to replace SQL-based ETL processes that you currently run on Apache Hive.

Although it is completely possible, you should be aware of some limitations that may affect your SLAs.

Read More

dmtolpeko
I/O, Snowflake

Snowflake – Micro-Partitions and Clustering Depth

December 2, 2019

Traditional data warehouses require you to explicitly specify partition columns for tables using the PARTITION BY clause. There is no PARTITION BY clause in the CREATE TABLE statement in Snowflake although it still heavily relies on partitions.

I already wrote about partitions in Snowflake (see, MIN/MAX Functions and Partition Pruning in Snowflake) but in this article I am going to investigate some more details.

Read More

dmtolpeko