Materialized Column: An Efficient Way to Optimize Queries on Nested Columns
2 likes543 views
In data warehouse area, it is common to use one or more columns in complex type, such as map, and put many subfields into it. It may impact the query performance dramatically because: 1) It is a waste of IO. The whole column (in map), which may contain tens of subfields, need to be read. And Spark will traverse the whole map and get the value of the target key. 2) Vectorized read can not be exploit when nested type column is read. 3) Filter pushdown can not be utilized when nested columns is read. Over the last year, we have added a series of optimizations in Apache Spark to solve the above problems for Parquet.
1 of 22
Download to read offline
![How does Materialized Column solve these problems
CREATE TABLE base_table (
item STRING,
count INT,
people<STRING, STRING>
date STRING
)
USING parquet
PARTITIONED BY (date);
ALTER TABLE base_table ADD COLUMNS
(
age INT MATERIALIZED CAST(peopl
e[‘age’] AS INTEGER)
);
Add materialized columnOriginal table](https://image.slidesharecdn.com/114junguo-201129183229/85/Materialized-Column-An-Efficient-Way-to-Optimize-Queries-on-Nested-Columns-17-320.jpg)
Ad
Recommended
Improving SparkSQL Performance by 30%: How We Optimize Parquet Pushdown and P...
Improving SparkSQL Performance by 30%: How We Optimize Parquet Pushdown and P...Databricks The document discusses optimizations made to Spark SQL performance when working with Parquet files at ByteDance. It describes how Spark originally reads Parquet files and identifies two main areas for optimization: Parquet filter pushdown and the Parquet reader. For filter pushdown, sorting columns improved statistics and reduced data reads by 30%. For the reader, splitting it to first filter then read other columns prevented loading unnecessary data. These changes improved Spark SQL performance at ByteDance without changing jobs.
Common Strategies for Improving Performance on Your Delta Lakehouse
Common Strategies for Improving Performance on Your Delta LakehouseDatabricks The Delta Architecture pattern has made the lives of data engineers much simpler, but what about improving query performance for data analysts? What are some common places to look at for tuning query performance? In this session we will cover some common techniques to apply to our delta tables to make them perform better for data analysts queries. We will look at a few examples of how you can analyze a query, and determine what to focus on to deliver better performance results.
Understanding Query Plans and Spark UIs
Understanding Query Plans and Spark UIsDatabricks "The common use cases of Spark SQL include ad hoc analysis, logical warehouse, query federation, and ETL processing. Spark SQL also powers the other Spark libraries, including structured streaming for stream processing, MLlib for machine learning, and GraphFrame for graph-parallel computation. For boosting the speed of your Spark applications, you can perform the optimization efforts on the queries prior employing to the production systems. Spark query plans and Spark UIs provide you insight on the performance of your queries. This talk discloses how to read and tune the query plans for enhanced performance. It will also cover the major related features in the recent and upcoming releases of Apache Spark.
"
How We Optimize Spark SQL Jobs With parallel and sync IO
How We Optimize Spark SQL Jobs With parallel and sync IODatabricks Although NVMe has been more and more popular these years, a large amount of HDD are still widely used in super-large scale big data clusters. In a EB-level data platform, IO(including decompression and decode) cost contributes a large proportion of Spark jobs’ cost. In another word, IO operation is worth optimizing.
In ByteDancen, we do a series of IO optimization to improve performance, including parallel read and asynchronized shuffle. Firstly we implement file level parallel read to improve performance when there are a lot of small files. Secondly, we design row group level parallel read to accelerate queries for big-file scenario. Thirdly, implement asynchronized spill to improve job peformance. Besides, we design parquet column family, which will split a table into a few column families and different column family will be in different Parquets files. Different column family can be read in parallel, so the read performance is much higher than the existing approach. In our practice, the end to end performance is improved by 5% to 30%
In this talk, I will illustrate how we implement these features and how they accelerate Apache Spark jobs.
Delta: Building Merge on Read
Delta: Building Merge on ReadDatabricks We can leverage Delta Lake, structured streaming for write-heavy use cases. This talk will go through a use case at Intuit whereby we built MOR as an architecture to allow for a very low SLA, etc. For MOR, there are different ways to view the fresh data, so we will also go over the methods used to perfTest the various ways that we were able to arrive at the best method for the given use case.
Spark SQL Beyond Official Documentation
Spark SQL Beyond Official DocumentationDatabricks Implementing efficient Spark application with the goal of having maximal performance often requires knowledge that goes beyond official documentation. Understanding Spark’s internal processes and features may help to design the queries in alignment with internal optimizations and thus achieve high efficiency during execution. In this talk we will focus on some internal features of Spark SQL which are not well described in official documentation with a strong emphasis on explaining these features on some basic examples while sharing some performance tips along the way.
Vectorized Query Execution in Apache Spark at Facebook
Vectorized Query Execution in Apache Spark at FacebookDatabricks This document summarizes Chen Yang's presentation on vectorized query execution in Apache Spark at Facebook. The key points are:
1) Spark is the largest SQL query engine at Facebook and uses columnar formats like ORC to improve storage efficiency.
2) Vectorized processing can improve performance over row-at-a-time processing by reducing per-row overhead and improving cache locality.
3) Facebook has implemented a vectorized ORC reader and writer in Spark that shows up to 8x speedup on microbenchmarks compared to the row-at-a-time approach.
PostgreSQL Tutorial For Beginners | Edureka
PostgreSQL Tutorial For Beginners | EdurekaEdureka! YouTube Link: https://youtu.be/-VO7YjQeG6Y
** MYSQL DBA Certification Training https://www.edureka.co/mysql-dba **
This Edureka PPT on PostgreSQL Tutorial For Beginners (blog: http://bit.ly/33GN7jQ) will help you learn PostgreSQL in depth. You will also learn how to install PostgreSQL on windows. The following topics will be covered in this session:
What is DBMS
What is SQL?
What is PostgreSQL?
Features of PostgreSQL
Install PostgreSQL
SQL Command Categories
DDL Commands
ER Diagram
Entity & Attributes
Keys in Database
Constraints in Database
Normalization
DML Commands
Operators
Nested Queries
Set Operations
Special Operators
Aggregate Functions
Limit, Offset & Fetch
Joins
Views
Procedures
Triggers
DCL Commands
TCL Commands
Export/ Import Data
UUID Datatype
Follow us to never miss an update in the future.
YouTube: https://www.youtube.com/user/edurekaIN
Instagram: https://www.instagram.com/edureka_learning/
Facebook: https://www.facebook.com/edurekaIN/
Twitter: https://twitter.com/edurekain
LinkedIn: https://www.linkedin.com/company/edureka
Castbox: https://castbox.fm/networks/505?country=in
The Rise of ZStandard: Apache Spark/Parquet/ORC/Avro
The Rise of ZStandard: Apache Spark/Parquet/ORC/AvroDatabricks Zstandard is a fast compression algorithm which you can use in Apache Spark in various way. In this talk, I briefly summarized the evolution history of Apache Spark in this area and four main use cases and the benefits and the next steps:
1) ZStandard can optimize Spark local disk IO by compressing shuffle files significantly. This is very useful in K8s environments. It’s beneficial not only when you use `emptyDir` with `memory` medium, but also it maximizes OS cache benefit when you use shared SSDs or container local storage. In Spark 3.2, SPARK-34390 takes advantage of ZStandard buffer pool feature and its performance gain is impressive, too.
2) Event log compression is another area to save your storage cost on the cloud storage like S3 and to improve the usability. SPARK-34503 officially switched the default event log compression codec from LZ4 to Zstandard.
3) Zstandard data file compression can give you more benefits when you use ORC/Parquet files as your input and output. Apache ORC 1.6 supports Zstandardalready and Apache Spark enables it via SPARK-33978. The upcoming Parquet 1.12 will support Zstandard compression.
4) Last, but not least, since Apache Spark 3.0, Zstandard is used to serialize/deserialize MapStatus data instead of Gzip.
There are more community works to utilize Zstandard to improve Spark. For example, Apache Avro community also supports Zstandard and SPARK-34479 aims to support Zstandard in Spark’s avro file format in Spark 3.2.0.
Understanding and Improving Code Generation
Understanding and Improving Code GenerationDatabricks Code generation is integral to Spark’s physical execution engine. When implemented, the Spark engine creates optimized bytecode at runtime improving performance when compared to interpreted execution. Spark has taken the next step with whole-stage codegen which collapses an entire query into a single function.
Deep Dive into Spark SQL with Advanced Performance Tuning with Xiao Li & Wenc...
Deep Dive into Spark SQL with Advanced Performance Tuning with Xiao Li & Wenc...Databricks Spark SQL is a highly scalable and efficient relational processing engine with ease-to-use APIs and mid-query fault tolerance. It is a core module of Apache Spark. Spark SQL can process, integrate and analyze the data from diverse data sources (e.g., Hive, Cassandra, Kafka and Oracle) and file formats (e.g., Parquet, ORC, CSV, and JSON). This talk will dive into the technical details of SparkSQL spanning the entire lifecycle of a query execution. The audience will get a deeper understanding of Spark SQL and understand how to tune Spark SQL performance.
Efficient Data Storage for Analytics with Apache Parquet 2.0
Efficient Data Storage for Analytics with Apache Parquet 2.0Cloudera, Inc. Apache Parquet is an open-source columnar storage format for efficient data storage and analytics. It provides efficient compression and encoding techniques that enable fast scans and queries of large datasets. Parquet 2.0 improves on these efficiencies through enhancements like delta encoding, binary packing designed for CPU efficiency, and predicate pushdown using statistics. Benchmark results show Parquet provides much better compression and query performance than row-oriented formats on big data workloads. The project is developed as an open-source community with contributions from many organizations.
Enhancing Spark SQL Optimizer with Reliable Statistics
Enhancing Spark SQL Optimizer with Reliable StatisticsJen Aman This document discusses enhancements to the Spark SQL optimizer through improved statistics collection and cost-based optimization rules. It describes collecting table and column statistics from Hive metastore and developing 1D and 2D histograms. New rules estimate operator costs based on output rows and size. Join order, filter statistics, and handling unique columns are discussed. Future work includes faster histogram collection, expression statistics, and continuous feedback optimization.
The Parquet Format and Performance Optimization Opportunities
The Parquet Format and Performance Optimization OpportunitiesDatabricks The Parquet format is one of the most widely used columnar storage formats in the Spark ecosystem. Given that I/O is expensive and that the storage layer is the entry point for any query execution, understanding the intricacies of your storage format is important for optimizing your workloads.
As an introduction, we will provide context around the format, covering the basics of structured data formats and the underlying physical data storage model alternatives (row-wise, columnar and hybrid). Given this context, we will dive deeper into specifics of the Parquet format: representation on disk, physical data organization (row-groups, column-chunks and pages) and encoding schemes. Now equipped with sufficient background knowledge, we will discuss several performance optimization opportunities with respect to the format: dictionary encoding, page compression, predicate pushdown (min/max skipping), dictionary filtering and partitioning schemes. We will learn how to combat the evil that is ‘many small files’, and will discuss the open-source Delta Lake format in relation to this and Parquet in general.
This talk serves both as an approachable refresher on columnar storage as well as a guide on how to leverage the Parquet format for speeding up analytical workloads in Spark using tangible tips and tricks.
Fine Tuning and Enhancing Performance of Apache Spark Jobs
Fine Tuning and Enhancing Performance of Apache Spark JobsDatabricks Apache Spark defaults provide decent performance for large data sets but leave room for significant performance gains if able to tune parameters based on resources and job.
Physical Plans in Spark SQL
Physical Plans in Spark SQLDatabricks In Spark SQL the physical plan provides the fundamental information about the execution of the query. The objective of this talk is to convey understanding and familiarity of query plans in Spark SQL, and use that knowledge to achieve better performance of Apache Spark queries. We will walk you through the most common operators you might find in the query plan and explain some relevant information that can be useful in order to understand some details about the execution. If you understand the query plan, you can look for the weak spot and try to rewrite the query to achieve a more optimal plan that leads to more efficient execution.
The main content of this talk is based on Spark source code but it will reflect some real-life queries that we run while processing data. We will show some examples of query plans and explain how to interpret them and what information can be taken from them. We will also describe what is happening under the hood when the plan is generated focusing mainly on the phase of physical planning. In general, in this talk we want to share what we have learned from both Spark source code and real-life queries that we run in our daily data processing.
Delta Lake: Optimizing Merge
Delta Lake: Optimizing MergeDatabricks This talk will break down merge in Delta Lake—what is actually happening under the hood—and then explain about how you can optimize a merge. There are even some code snippet and sample configs that will be shared.
Deep Dive: Memory Management in Apache Spark
Deep Dive: Memory Management in Apache SparkDatabricks Memory management is at the heart of any data-intensive system. Spark, in particular, must arbitrate memory allocation between two main use cases: buffering intermediate data for processing (execution) and caching user data (storage). This talk will take a deep dive through the memory management designs adopted in Spark since its inception and discuss their performance and usability implications for the end user.
Memory Management in Apache Spark
Memory Management in Apache SparkDatabricks Memory management is at the heart of any data-intensive system. Spark, in particular, must arbitrate memory allocation between two main use cases: buffering intermediate data for processing (execution) and caching user data (storage). This talk will take a deep dive through the memory management designs adopted in Spark since its inception and discuss their performance and usability implications for the end user.
Apache Spark Core—Deep Dive—Proper Optimization
Apache Spark Core—Deep Dive—Proper OptimizationDatabricks Optimizing spark jobs through a true understanding of spark core. Learn: What is a partition? What is the difference between read/shuffle/write partitions? How to increase parallelism and decrease output files? Where does shuffle data go between stages? What is the "right" size for your spark partitions and files? Why does a job slow down with only a few tasks left and never finish? Why doesn't adding nodes decrease my compute time?
Change Data Feed in Delta
Change Data Feed in DeltaDatabricks This document discusses Delta Change Data Feed (CDF), which allows capturing changes made to Delta tables. It describes how CDF works by storing change events like inserts, updates and deletes. It also outlines how CDF can be used to improve ETL pipelines, unify batch and streaming workflows, and meet regulatory needs. The document provides examples of enabling CDF, querying change data and storing the change events. It concludes by offering a demo of CDF in Jupyter notebooks.
Adaptive Query Execution: Speeding Up Spark SQL at Runtime
Adaptive Query Execution: Speeding Up Spark SQL at RuntimeDatabricks Over the years, there has been extensive and continuous effort on improving Spark SQL’s query optimizer and planner, in order to generate high quality query execution plans. One of the biggest improvements is the cost-based optimization framework that collects and leverages a variety of data statistics (e.g., row count, number of distinct values, NULL values, max/min values, etc.) to help Spark make better decisions in picking the most optimal query plan.
Bucketing 2.0: Improve Spark SQL Performance by Removing Shuffle
Bucketing 2.0: Improve Spark SQL Performance by Removing ShuffleDatabricks Bucketing is commonly used in Hive and Spark SQL to improve performance by eliminating Shuffle in Join or group-by-aggregate scenario. This is ideal for a variety of write-once and read-many datasets at Bytedance.
A Deep Dive into Spark SQL's Catalyst Optimizer with Yin Huai
A Deep Dive into Spark SQL's Catalyst Optimizer with Yin HuaiDatabricks Catalyst is becoming one of the most important components of Apache Spark, as it underpins all the major new APIs in Spark 2.0 and later versions, from DataFrames and Datasets to Streaming. At its core, Catalyst is a general library for manipulating trees.
In this talk, Yin explores a modular compiler frontend for Spark based on this library that includes a query analyzer, optimizer, and an execution planner. Yin offers a deep dive into Spark SQL’s Catalyst optimizer, introducing the core concepts of Catalyst and demonstrating how developers can extend it. You’ll leave with a deeper understanding of how Spark analyzes, optimizes, and plans a user’s query.
Spark shuffle introduction
Spark shuffle introductioncolorant This document discusses Spark shuffle, which is an expensive operation that involves data partitioning, serialization/deserialization, compression, and disk I/O. It provides an overview of how shuffle works in Spark and the history of optimizations like sort-based shuffle and an external shuffle service. Key concepts discussed include shuffle writers, readers, and the pluggable block transfer service that handles data transfer. The document also covers shuffle-related configuration options and potential future work.
Deep Dive into the New Features of Apache Spark 3.0
Deep Dive into the New Features of Apache Spark 3.0Databricks Continuing with the objectives to make Spark faster, easier, and smarter, Apache Spark 3.0 extends its scope with more than 3000 resolved JIRAs. We will talk about the exciting new developments in the Spark 3.0 as well as some other major initiatives that are coming in the future.
Making Nested Columns as First Citizen in Apache Spark SQL
Making Nested Columns as First Citizen in Apache Spark SQLDatabricks Apple Siri is the world's largest virtual assistant service powering every iPhone, iPad, Mac, Apple TV, Apple Watch, and HomePod. We use large amounts of data to provide our users the best possible personalized experience. Our raw event data is cleaned and pre-joined into an unified data for our data consumers to use. To keep the rich hierarchical structure of the data, our data schemas are very deep nested structures. In this talk, we will discuss how Spark handles nested structures in Spark 2.4, and we'll show the fundamental design issues in reading nested fields which is not being well considered when Spark SQL was designed. This results in Spark SQL reading unnecessary data in many operations. Given that Siri's data is super nested and humongous, this soon becomes a bottleneck in our pipelines. Then we will talk about the various approaches we have taken to tackle this problem. By making nested columns as first citizen in Spark SQL, we can achieve dramatic performance gain. In some of our production queries, the speed-up can be 20x in wall clock time and 8x less data being read. All of our work will be open source, and some has already been merged into upstream.
Spark + Parquet In Depth: Spark Summit East Talk by Emily Curtin and Robbie S...
Spark + Parquet In Depth: Spark Summit East Talk by Emily Curtin and Robbie S...Spark Summit What if you could get the simplicity, convenience, interoperability, and storage niceties of an old-fashioned CSV with the speed of a NoSQL database and the storage requirements of a gzipped file? Enter Parquet.
At The Weather Company, Parquet files are a quietly awesome and deeply integral part of our Spark-driven analytics workflow. Using Spark + Parquet, we’ve built a blazing fast, storage-efficient, query-efficient data lake and a suite of tools to accompany it.
We will give a technical overview of how Parquet works and how recent improvements from Tungsten enable SparkSQL to take advantage of this design to provide fast queries by overcoming two major bottlenecks of distributed analytics: communication costs (IO bound) and data decoding (CPU bound).
The Science of DBMS: Data Storage & Organization 
The Science of DBMS: Data Storage & Organization SAP Technology This session will take a look at data storage and compression/encryption and discuss the different techniques for organizing data on disk along with the tradeoffs of the different types of common compression considerations and the impacts of encryption. Familiarity with space allocation in ASE is assumed.
The thinking persons guide to data warehouse design
The thinking persons guide to data warehouse designCalpont The document discusses key considerations for designing a data warehouse, including building a logical design, transitioning to a physical design, and monitoring and tuning the design. It recommends using a modeling tool to capture logical designs, manual partitioning in some cases, and letting database engines do the work. It also covers physical design decisions like SQL vs NoSQL, row vs column storage, partitioning, indexing and optimizing data loads. Regular monitoring of workloads, bottlenecks and ratios is advised to tune performance.
More Related Content
What's hot (20)
The Rise of ZStandard: Apache Spark/Parquet/ORC/Avro
The Rise of ZStandard: Apache Spark/Parquet/ORC/AvroDatabricks Zstandard is a fast compression algorithm which you can use in Apache Spark in various way. In this talk, I briefly summarized the evolution history of Apache Spark in this area and four main use cases and the benefits and the next steps:
1) ZStandard can optimize Spark local disk IO by compressing shuffle files significantly. This is very useful in K8s environments. It’s beneficial not only when you use `emptyDir` with `memory` medium, but also it maximizes OS cache benefit when you use shared SSDs or container local storage. In Spark 3.2, SPARK-34390 takes advantage of ZStandard buffer pool feature and its performance gain is impressive, too.
2) Event log compression is another area to save your storage cost on the cloud storage like S3 and to improve the usability. SPARK-34503 officially switched the default event log compression codec from LZ4 to Zstandard.
3) Zstandard data file compression can give you more benefits when you use ORC/Parquet files as your input and output. Apache ORC 1.6 supports Zstandardalready and Apache Spark enables it via SPARK-33978. The upcoming Parquet 1.12 will support Zstandard compression.
4) Last, but not least, since Apache Spark 3.0, Zstandard is used to serialize/deserialize MapStatus data instead of Gzip.
There are more community works to utilize Zstandard to improve Spark. For example, Apache Avro community also supports Zstandard and SPARK-34479 aims to support Zstandard in Spark’s avro file format in Spark 3.2.0.
Understanding and Improving Code Generation
Understanding and Improving Code GenerationDatabricks Code generation is integral to Spark’s physical execution engine. When implemented, the Spark engine creates optimized bytecode at runtime improving performance when compared to interpreted execution. Spark has taken the next step with whole-stage codegen which collapses an entire query into a single function.
Deep Dive into Spark SQL with Advanced Performance Tuning with Xiao Li & Wenc...
Deep Dive into Spark SQL with Advanced Performance Tuning with Xiao Li & Wenc...Databricks Spark SQL is a highly scalable and efficient relational processing engine with ease-to-use APIs and mid-query fault tolerance. It is a core module of Apache Spark. Spark SQL can process, integrate and analyze the data from diverse data sources (e.g., Hive, Cassandra, Kafka and Oracle) and file formats (e.g., Parquet, ORC, CSV, and JSON). This talk will dive into the technical details of SparkSQL spanning the entire lifecycle of a query execution. The audience will get a deeper understanding of Spark SQL and understand how to tune Spark SQL performance.
Efficient Data Storage for Analytics with Apache Parquet 2.0
Efficient Data Storage for Analytics with Apache Parquet 2.0Cloudera, Inc. Apache Parquet is an open-source columnar storage format for efficient data storage and analytics. It provides efficient compression and encoding techniques that enable fast scans and queries of large datasets. Parquet 2.0 improves on these efficiencies through enhancements like delta encoding, binary packing designed for CPU efficiency, and predicate pushdown using statistics. Benchmark results show Parquet provides much better compression and query performance than row-oriented formats on big data workloads. The project is developed as an open-source community with contributions from many organizations.
Enhancing Spark SQL Optimizer with Reliable Statistics
Enhancing Spark SQL Optimizer with Reliable StatisticsJen Aman This document discusses enhancements to the Spark SQL optimizer through improved statistics collection and cost-based optimization rules. It describes collecting table and column statistics from Hive metastore and developing 1D and 2D histograms. New rules estimate operator costs based on output rows and size. Join order, filter statistics, and handling unique columns are discussed. Future work includes faster histogram collection, expression statistics, and continuous feedback optimization.
The Parquet Format and Performance Optimization Opportunities
The Parquet Format and Performance Optimization OpportunitiesDatabricks The Parquet format is one of the most widely used columnar storage formats in the Spark ecosystem. Given that I/O is expensive and that the storage layer is the entry point for any query execution, understanding the intricacies of your storage format is important for optimizing your workloads.
As an introduction, we will provide context around the format, covering the basics of structured data formats and the underlying physical data storage model alternatives (row-wise, columnar and hybrid). Given this context, we will dive deeper into specifics of the Parquet format: representation on disk, physical data organization (row-groups, column-chunks and pages) and encoding schemes. Now equipped with sufficient background knowledge, we will discuss several performance optimization opportunities with respect to the format: dictionary encoding, page compression, predicate pushdown (min/max skipping), dictionary filtering and partitioning schemes. We will learn how to combat the evil that is ‘many small files’, and will discuss the open-source Delta Lake format in relation to this and Parquet in general.
This talk serves both as an approachable refresher on columnar storage as well as a guide on how to leverage the Parquet format for speeding up analytical workloads in Spark using tangible tips and tricks.
Fine Tuning and Enhancing Performance of Apache Spark Jobs
Fine Tuning and Enhancing Performance of Apache Spark JobsDatabricks Apache Spark defaults provide decent performance for large data sets but leave room for significant performance gains if able to tune parameters based on resources and job.
Physical Plans in Spark SQL
Physical Plans in Spark SQLDatabricks In Spark SQL the physical plan provides the fundamental information about the execution of the query. The objective of this talk is to convey understanding and familiarity of query plans in Spark SQL, and use that knowledge to achieve better performance of Apache Spark queries. We will walk you through the most common operators you might find in the query plan and explain some relevant information that can be useful in order to understand some details about the execution. If you understand the query plan, you can look for the weak spot and try to rewrite the query to achieve a more optimal plan that leads to more efficient execution.
The main content of this talk is based on Spark source code but it will reflect some real-life queries that we run while processing data. We will show some examples of query plans and explain how to interpret them and what information can be taken from them. We will also describe what is happening under the hood when the plan is generated focusing mainly on the phase of physical planning. In general, in this talk we want to share what we have learned from both Spark source code and real-life queries that we run in our daily data processing.
Delta Lake: Optimizing Merge
Delta Lake: Optimizing MergeDatabricks This talk will break down merge in Delta Lake—what is actually happening under the hood—and then explain about how you can optimize a merge. There are even some code snippet and sample configs that will be shared.
Deep Dive: Memory Management in Apache Spark
Deep Dive: Memory Management in Apache SparkDatabricks Memory management is at the heart of any data-intensive system. Spark, in particular, must arbitrate memory allocation between two main use cases: buffering intermediate data for processing (execution) and caching user data (storage). This talk will take a deep dive through the memory management designs adopted in Spark since its inception and discuss their performance and usability implications for the end user.
Memory Management in Apache Spark
Memory Management in Apache SparkDatabricks Memory management is at the heart of any data-intensive system. Spark, in particular, must arbitrate memory allocation between two main use cases: buffering intermediate data for processing (execution) and caching user data (storage). This talk will take a deep dive through the memory management designs adopted in Spark since its inception and discuss their performance and usability implications for the end user.
Apache Spark Core—Deep Dive—Proper Optimization
Apache Spark Core—Deep Dive—Proper OptimizationDatabricks Optimizing spark jobs through a true understanding of spark core. Learn: What is a partition? What is the difference between read/shuffle/write partitions? How to increase parallelism and decrease output files? Where does shuffle data go between stages? What is the "right" size for your spark partitions and files? Why does a job slow down with only a few tasks left and never finish? Why doesn't adding nodes decrease my compute time?
Change Data Feed in Delta
Change Data Feed in DeltaDatabricks This document discusses Delta Change Data Feed (CDF), which allows capturing changes made to Delta tables. It describes how CDF works by storing change events like inserts, updates and deletes. It also outlines how CDF can be used to improve ETL pipelines, unify batch and streaming workflows, and meet regulatory needs. The document provides examples of enabling CDF, querying change data and storing the change events. It concludes by offering a demo of CDF in Jupyter notebooks.
Adaptive Query Execution: Speeding Up Spark SQL at Runtime
Adaptive Query Execution: Speeding Up Spark SQL at RuntimeDatabricks Over the years, there has been extensive and continuous effort on improving Spark SQL’s query optimizer and planner, in order to generate high quality query execution plans. One of the biggest improvements is the cost-based optimization framework that collects and leverages a variety of data statistics (e.g., row count, number of distinct values, NULL values, max/min values, etc.) to help Spark make better decisions in picking the most optimal query plan.
Bucketing 2.0: Improve Spark SQL Performance by Removing Shuffle
Bucketing 2.0: Improve Spark SQL Performance by Removing ShuffleDatabricks Bucketing is commonly used in Hive and Spark SQL to improve performance by eliminating Shuffle in Join or group-by-aggregate scenario. This is ideal for a variety of write-once and read-many datasets at Bytedance.
A Deep Dive into Spark SQL's Catalyst Optimizer with Yin Huai
A Deep Dive into Spark SQL's Catalyst Optimizer with Yin HuaiDatabricks Catalyst is becoming one of the most important components of Apache Spark, as it underpins all the major new APIs in Spark 2.0 and later versions, from DataFrames and Datasets to Streaming. At its core, Catalyst is a general library for manipulating trees.
In this talk, Yin explores a modular compiler frontend for Spark based on this library that includes a query analyzer, optimizer, and an execution planner. Yin offers a deep dive into Spark SQL’s Catalyst optimizer, introducing the core concepts of Catalyst and demonstrating how developers can extend it. You’ll leave with a deeper understanding of how Spark analyzes, optimizes, and plans a user’s query.
Spark shuffle introduction
Spark shuffle introductioncolorant This document discusses Spark shuffle, which is an expensive operation that involves data partitioning, serialization/deserialization, compression, and disk I/O. It provides an overview of how shuffle works in Spark and the history of optimizations like sort-based shuffle and an external shuffle service. Key concepts discussed include shuffle writers, readers, and the pluggable block transfer service that handles data transfer. The document also covers shuffle-related configuration options and potential future work.
Deep Dive into the New Features of Apache Spark 3.0
Deep Dive into the New Features of Apache Spark 3.0Databricks Continuing with the objectives to make Spark faster, easier, and smarter, Apache Spark 3.0 extends its scope with more than 3000 resolved JIRAs. We will talk about the exciting new developments in the Spark 3.0 as well as some other major initiatives that are coming in the future.
Making Nested Columns as First Citizen in Apache Spark SQL
Making Nested Columns as First Citizen in Apache Spark SQLDatabricks Apple Siri is the world's largest virtual assistant service powering every iPhone, iPad, Mac, Apple TV, Apple Watch, and HomePod. We use large amounts of data to provide our users the best possible personalized experience. Our raw event data is cleaned and pre-joined into an unified data for our data consumers to use. To keep the rich hierarchical structure of the data, our data schemas are very deep nested structures. In this talk, we will discuss how Spark handles nested structures in Spark 2.4, and we'll show the fundamental design issues in reading nested fields which is not being well considered when Spark SQL was designed. This results in Spark SQL reading unnecessary data in many operations. Given that Siri's data is super nested and humongous, this soon becomes a bottleneck in our pipelines. Then we will talk about the various approaches we have taken to tackle this problem. By making nested columns as first citizen in Spark SQL, we can achieve dramatic performance gain. In some of our production queries, the speed-up can be 20x in wall clock time and 8x less data being read. All of our work will be open source, and some has already been merged into upstream.
Spark + Parquet In Depth: Spark Summit East Talk by Emily Curtin and Robbie S...
Spark + Parquet In Depth: Spark Summit East Talk by Emily Curtin and Robbie S...Spark Summit What if you could get the simplicity, convenience, interoperability, and storage niceties of an old-fashioned CSV with the speed of a NoSQL database and the storage requirements of a gzipped file? Enter Parquet.
At The Weather Company, Parquet files are a quietly awesome and deeply integral part of our Spark-driven analytics workflow. Using Spark + Parquet, we’ve built a blazing fast, storage-efficient, query-efficient data lake and a suite of tools to accompany it.
We will give a technical overview of how Parquet works and how recent improvements from Tungsten enable SparkSQL to take advantage of this design to provide fast queries by overcoming two major bottlenecks of distributed analytics: communication costs (IO bound) and data decoding (CPU bound).
Similar to Materialized Column: An Efficient Way to Optimize Queries on Nested Columns (20)
The Science of DBMS: Data Storage & Organization
The Science of DBMS: Data Storage & Organization SAP Technology This session will take a look at data storage and compression/encryption and discuss the different techniques for organizing data on disk along with the tradeoffs of the different types of common compression considerations and the impacts of encryption. Familiarity with space allocation in ASE is assumed.
The thinking persons guide to data warehouse design
The thinking persons guide to data warehouse designCalpont The document discusses key considerations for designing a data warehouse, including building a logical design, transitioning to a physical design, and monitoring and tuning the design. It recommends using a modeling tool to capture logical designs, manual partitioning in some cases, and letting database engines do the work. It also covers physical design decisions like SQL vs NoSQL, row vs column storage, partitioning, indexing and optimizing data loads. Regular monitoring of workloads, bottlenecks and ratios is advised to tune performance.
Ibm redbook
Ibm redbookRahul Verma The document summarizes a new 660-page IBM RedBook about DataStage documentation and examples. It provides overviews of DataStage architecture, best practices, popular stage descriptions, and a retail processing scenario with hundreds of pages and downloadable files. The RedBook aims to address past complaints about a lack of DataStage documentation by providing extensive guidelines, tips and examples.
MWLUG 2016 : AD117 : Xpages & jQuery DataTables
MWLUG 2016 : AD117 : Xpages & jQuery DataTablesMichael Smith - DataTables is a jQuery plugin that enhances the accessibility of data in HTML tables. It allows for easy creation of rich, interactive views in XPages applications.
- Data can be added to DataTables from HTML, a JavaScript array, or an Ajax data source like REST. Callbacks provide a way to add interactivity similar to the XPages lifecycle.
- Advanced configuration options include click handlers, renderers, filtering, lazy loading, and categorization to create feature-rich views.
The Science of DBMS: Query Optimization 
The Science of DBMS: Query Optimization SAP Technology This session will take a look at when/how query optimization takes place, the resources used for query optimization, the role of index statistics and common application query problems (other than simplistic missing indexes) that lead to DBA’s assuming there is a query optimization issue.
Best practice bi_design_bestpracticesv_1_5
Best practice bi_design_bestpracticesv_1_5rajibzzaman This document discusses best practices for designing and tuning Oracle Business Intelligence 11g repositories, dashboards, reports, and queries. It covers topics such as repository design, including physical layer, business model, and presentation layer considerations. It also discusses dashboard and report design best practices, reading the query log, and performance tuning for both relational and multidimensional databases. The document provides an agenda and guidelines for each topic area.
The Future of Fast Databases: Lessons from a Decade of QuestDB
The Future of Fast Databases: Lessons from a Decade of QuestDBjavier ramirez Over the last decade, QuestDB has been at the forefront of handling time series data with a focus on speed and efficiency.
In this talk, I’ll share practical insights from our experience serving thousands of users, highlighting what we’ve learned about building and maintaining a fast database that can ingest millions of events per second.
QuestDB, an open-source time series database, has traditionally relied on a custom-built, non-standard data storage format designed for performance. As we move forward, we’re actively developing its architecture to support open formats like Apache Parquet and Arrow, reflecting a broader industry shift.
I’ll discuss the engineering challenges we’ve faced during this transition, the new possibilities it creates, and why these changes are crucial for the evolving database landscape.
Through live demos, I’ll showcase QuestDB’s performance in real-time data ingestion and queries, and demonstrate some of the features enabled by these new formats.
HBaseCon 2012 | HBase Schema Design - Ian Varley, Salesforce
HBaseCon 2012 | HBase Schema Design - Ian Varley, SalesforceCloudera, Inc. Most developers are familiar with the topic of “database design”. In the relational world, normalization is the name of the game. How do things change when you’re working with a scalable, distributed, non-SQL database like HBase? This talk will cover the basics of HBase schema design at a high level and give several common patterns and examples of real-world schemas to solve interesting problems. The storage and data access architecture of HBase (row keys, column families, etc.) will be explained, along with the pros and cons of different schema decisions.
SQL Pass Summit Presentations from Datavail - Optimize SQL Server: Query Tuni...
SQL Pass Summit Presentations from Datavail - Optimize SQL Server: Query Tuni...Datavail Our database experts, Rajnikant Tandel and Anup Gopinathan, will show you how to identify and fine tune your problem queries to make a significant impact on the overall performance of your database.
GIDS 2016 Understanding and Building No SQLs
GIDS 2016 Understanding and Building No SQLstechmaddy Storage becomes the key part of any Big Data system. There are few non-functional parameters that are expected from the Big Data storage systems like reliability, horizontal scalability, high availability, fault tolerance, etc. To support these properties and the change of data storage and access patterns in Big Data systems lead to a class of storage - NoSQLs. If there’s one rule in design -- there will always be trade-offs. CAP theorem defines the choices that we can make with the trade-offs. And ACID rules change to BASE in NoSQLs.
This talk focuses on understanding NoSQLs, the design decisions for designing NoSQL databases, an complete design example of key-value database, and patterns of replication and sharding.
Pl sql best practices document
Pl sql best practices documentAshwani Pandey This document provides guidelines for developing PL/SQL components including naming conventions, formatting, commenting practices, and optimizations. Key guidelines include using prefixes for different object types, indenting with 3 spaces, writing descriptive header comments, avoiding unnecessary full table scans, and leveraging collections like nested tables for persistence. Performance best practices focus on proper indexing, avoiding context switching between SQL and PL/SQL, and bulk operations over iterative processing.
Ledingkart Meetup #2: Scaling Search @Lendingkart
Ledingkart Meetup #2: Scaling Search @LendingkartMukesh Singh Scaling Search at Lendingkart discusses how Lendingkart scaled their search capabilities to handle large increases in data volume. They initially tried scaling databases vertically and horizontally, but searches were still slow at 8 seconds. They implemented ElasticSearch for its near real-time search, high scalability, and out-of-the-box functionality. Logstash was used to seed data from MySQL and MongoDB into ElasticSearch. Custom analyzers and mappings were developed. Searches then reduced to 230ms and aggregations to 200ms, allowing the business to scale as transactional data grew 3000% and leads 250%.
World2016_T5_S7_TeradataFunctionalOverview
World2016_T5_S7_TeradataFunctionalOverviewFarah Omer MicroStrategy and Teradata have a long partnership in providing business intelligence capabilities. MicroStrategy is optimized to run on Teradata and leverages many Teradata features and extensions for performance and scalability. These include multi-pass SQL, bulk inserts, Teradata indexing, functions, and syntax. MicroStrategy also integrates with Teradata tools and provides additional functionality like middle-tier computations and caching.
Myth busters - performance tuning 102 2008
Myth busters - performance tuning 102 2008paulguerin The document provides an overview of various techniques for optimizing database and application performance. It discusses fundamentals like minimizing logical I/O, balancing workload, and serial processing. It also covers the cost-based optimizer, column constraints and indexes, SQL tuning tips, subqueries vs joins, and non-SQL issues like undo storage and data migrations. Key recommendations include using column constraints, focusing on serial processing per table, and not over-relying on statistics to solve all performance problems.
SPL_ALL_EN.pptx
SPL_ALL_EN.pptx政宏 张 Give you a brief overview of the product. - What is esProc SPL? And show some cases helping you to know what it uses for. Talk about why esProc works better. And overview its brief characteristics. After that, Introduce the main technical solutions which esProc is often used.
Dan Hotka's Top 10 Oracle 12c New Features
Dan Hotka's Top 10 Oracle 12c New FeaturesEmbarcadero Technologies Watch the full webinar at: http://embt.co/1pb4Zb4
This presentation is a must-see for anyone interested in Oracle 12! Dan is an Oracle ACE Director and has assembled this presentation with fresh and inside information from Oracle Corp and OOW13. Dan has pulled his top Oracle 12 features from the plethora of new features available and documented in his user group presentations "Oracle 12c New Features for Developers" and "Oracle 12c New Features for DBA's".
Top 10 features will include:
New SQL Syntax
New SQL and PL/SQL Limits
Pluggable Database
New Packages
Deprecated Features
New SQL Tuning Features
This presentation covers new SQL & PL/SQL syntax and options, the container DB of course, new SQL optimizer features, deprecated features, hints, and more. If you're supporting applications, then you won't want to miss this webinar!
Seatug Presentation (Excel to Data Viz culture) Seattle Tableau User Group
Seatug Presentation (Excel to Data Viz culture) Seattle Tableau User GroupRussell Spangler This document discusses a Tableau user group meeting focused on transitioning from Excel to data visualization using Tableau. The meeting will feature presentations from two Tableau experts at Amazon on their experience using Tableau. The objectives of the meeting are explained, including comparing Excel and Tableau, overcoming data obstacles, design tips, and real world examples. Tips are provided on leveraging Tableau's capabilities, assessing existing Excel reports, starting out with Tableau, and achieving the goal of transitioning to Tableau.
Taming the shrew Power BI
Taming the shrew Power BIKellyn Pot'Vin-Gorman This document discusses techniques for optimizing Power BI performance. It recommends tracing queries using DAX Studio to identify slow queries and refresh times. Tracing tools like SQL Profiler and log files can provide insights into issues occurring in the data sources, Power BI layer, and across the network. Focusing on optimization by addressing wait times through a scientific process can help resolve long-term performance problems.
MySQL Optimizer: What's New in 8.0
MySQL Optimizer: What's New in 8.0Manyi Lu The document discusses new features and improvements in the MySQL 8.0 optimizer. Key highlights include:
- New SQL syntax like SELECT...FOR UPDATE SKIP LOCKED and NOWAIT to handle row locking contention.
- Support for common table expressions to improve readability and allow referencing derived tables multiple times.
- Enhancements to the cost model to produce more accurate estimates based on factors like data location.
- Better support for data types like UUID and IPv6, including optimized storage formats and new functions.
Recent MariaDB features to learn for a happy life
Recent MariaDB features to learn for a happy lifeFederico Razzoli After MariaDB 10.6 LTS was made available last year, three Short Term Support versions were released. While they shouldn’t be used in production, they allow us to test the features that will be included in the next LTS version. I follow the development of MariaDB through their JIRA, I test the new features, and I regularly review each new major version on the Vettabase website. In this talk I will summarise the most relevant features, show how to use them, and discuss how we can leverage them for real-world cases.
Ad
More from Databricks (20)
DW Migration Webinar-March 2022.pptx
DW Migration Webinar-March 2022.pptxDatabricks The document discusses migrating a data warehouse to the Databricks Lakehouse Platform. It outlines why legacy data warehouses are struggling, how the Databricks Platform addresses these issues, and key considerations for modern analytics and data warehousing. The document then provides an overview of the migration methodology, approach, strategies, and key takeaways for moving to a lakehouse on Databricks.
Data Lakehouse Symposium | Day 1 | Part 1
Data Lakehouse Symposium | Day 1 | Part 1Databricks The world of data architecture began with applications. Next came data warehouses. Then text was organized into a data warehouse.
Then one day the world discovered a whole new kind of data that was being generated by organizations. The world found that machines generated data that could be transformed into valuable insights. This was the origin of what is today called the data lakehouse. The evolution of data architecture continues today.
Come listen to industry experts describe this transformation of ordinary data into a data architecture that is invaluable to business. Simply put, organizations that take data architecture seriously are going to be at the forefront of business tomorrow.
This is an educational event.
Several of the authors of the book Building the Data Lakehouse will be presenting at this symposium.
Data Lakehouse Symposium | Day 1 | Part 2
Data Lakehouse Symposium | Day 1 | Part 2Databricks The world of data architecture began with applications. Next came data warehouses. Then text was organized into a data warehouse.
Then one day the world discovered a whole new kind of data that was being generated by organizations. The world found that machines generated data that could be transformed into valuable insights. This was the origin of what is today called the data lakehouse. The evolution of data architecture continues today.
Come listen to industry experts describe this transformation of ordinary data into a data architecture that is invaluable to business. Simply put, organizations that take data architecture seriously are going to be at the forefront of business tomorrow.
This is an educational event.
Several of the authors of the book Building the Data Lakehouse will be presenting at this symposium.
Data Lakehouse Symposium | Day 2
Data Lakehouse Symposium | Day 2Databricks The world of data architecture began with applications. Next came data warehouses. Then text was organized into a data warehouse.
Then one day the world discovered a whole new kind of data that was being generated by organizations. The world found that machines generated data that could be transformed into valuable insights. This was the origin of what is today called the data lakehouse. The evolution of data architecture continues today.
Come listen to industry experts describe this transformation of ordinary data into a data architecture that is invaluable to business. Simply put, organizations that take data architecture seriously are going to be at the forefront of business tomorrow.
This is an educational event.
Several of the authors of the book Building the Data Lakehouse will be presenting at this symposium.
Data Lakehouse Symposium | Day 4
Data Lakehouse Symposium | Day 4Databricks The document discusses the challenges of modern data, analytics, and AI workloads. Most enterprises struggle with siloed data systems that make integration and productivity difficult. The future of data lies with a data lakehouse platform that can unify data engineering, analytics, data warehousing, and machine learning workloads on a single open platform. The Databricks Lakehouse platform aims to address these challenges with its open data lake approach and capabilities for data engineering, SQL analytics, governance, and machine learning.
5 Critical Steps to Clean Your Data Swamp When Migrating Off of Hadoop
5 Critical Steps to Clean Your Data Swamp When Migrating Off of HadoopDatabricks In this session, learn how to quickly supplement your on-premises Hadoop environment with a simple, open, and collaborative cloud architecture that enables you to generate greater value with scaled application of analytics and AI on all your data. You will also learn five critical steps for a successful migration to the Databricks Lakehouse Platform along with the resources available to help you begin to re-skill your data teams.
Democratizing Data Quality Through a Centralized Platform
Democratizing Data Quality Through a Centralized PlatformDatabricks Bad data leads to bad decisions and broken customer experiences. Organizations depend on complete and accurate data to power their business, maintain efficiency, and uphold customer trust. With thousands of datasets and pipelines running, how do we ensure that all data meets quality standards, and that expectations are clear between producers and consumers? Investing in shared, flexible components and practices for monitoring data health is crucial for a complex data organization to rapidly and effectively scale.
At Zillow, we built a centralized platform to meet our data quality needs across stakeholders. The platform is accessible to engineers, scientists, and analysts, and seamlessly integrates with existing data pipelines and data discovery tools. In this presentation, we will provide an overview of our platform’s capabilities, including:
Giving producers and consumers the ability to define and view data quality expectations using a self-service onboarding portal
Performing data quality validations using libraries built to work with spark
Dynamically generating pipelines that can be abstracted away from users
Flagging data that doesn’t meet quality standards at the earliest stage and giving producers the opportunity to resolve issues before use by downstream consumers
Exposing data quality metrics alongside each dataset to provide producers and consumers with a comprehensive picture of health over time
Learn to Use Databricks for Data Science
Learn to Use Databricks for Data ScienceDatabricks Data scientists face numerous challenges throughout the data science workflow that hinder productivity. As organizations continue to become more data-driven, a collaborative environment is more critical than ever — one that provides easier access and visibility into the data, reports and dashboards built against the data, reproducibility, and insights uncovered within the data.. Join us to hear how Databricks’ open and collaborative platform simplifies data science by enabling you to run all types of analytics workloads, from data preparation to exploratory analysis and predictive analytics, at scale — all on one unified platform.
Why APM Is Not the Same As ML Monitoring
Why APM Is Not the Same As ML MonitoringDatabricks Application performance monitoring (APM) has become the cornerstone of software engineering allowing engineering teams to quickly identify and remedy production issues. However, as the world moves to intelligent software applications that are built using machine learning, traditional APM quickly becomes insufficient to identify and remedy production issues encountered in these modern software applications.
As a lead software engineer at NewRelic, my team built high-performance monitoring systems including Insights, Mobile, and SixthSense. As I transitioned to building ML Monitoring software, I found the architectural principles and design choices underlying APM to not be a good fit for this brand new world. In fact, blindly following APM designs led us down paths that would have been better left unexplored.
In this talk, I draw upon my (and my team’s) experience building an ML Monitoring system from the ground up and deploying it on customer workloads running large-scale ML training with Spark as well as real-time inference systems. I will highlight how the key principles and architectural choices of APM don’t apply to ML monitoring. You’ll learn why, understand what ML Monitoring can successfully borrow from APM, and hear what is required to build a scalable, robust ML Monitoring architecture.
The Function, the Context, and the Data—Enabling ML Ops at Stitch Fix
The Function, the Context, and the Data—Enabling ML Ops at Stitch FixDatabricks Autonomy and ownership are core to working at Stitch Fix, particularly on the Algorithms team. We enable data scientists to deploy and operate their models independently, with minimal need for handoffs or gatekeeping. By writing a simple function and calling out to an intuitive API, data scientists can harness a suite of platform-provided tooling meant to make ML operations easy. In this talk, we will dive into the abstractions the Data Platform team has built to enable this. We will go over the interface data scientists use to specify a model and what that hooks into, including online deployment, batch execution on Spark, and metrics tracking and visualization.
Stage Level Scheduling Improving Big Data and AI Integration
Stage Level Scheduling Improving Big Data and AI IntegrationDatabricks In this talk, I will dive into the stage level scheduling feature added to Apache Spark 3.1. Stage level scheduling extends upon Project Hydrogen by improving big data ETL and AI integration and also enables multiple other use cases. It is beneficial any time the user wants to change container resources between stages in a single Apache Spark application, whether those resources are CPU, Memory or GPUs. One of the most popular use cases is enabling end-to-end scalable Deep Learning and AI to efficiently use GPU resources. In this type of use case, users read from a distributed file system, do data manipulation and filtering to get the data into a format that the Deep Learning algorithm needs for training or inference and then sends the data into a Deep Learning algorithm. Using stage level scheduling combined with accelerator aware scheduling enables users to seamlessly go from ETL to Deep Learning running on the GPU by adjusting the container requirements for different stages in Spark within the same application. This makes writing these applications easier and can help with hardware utilization and costs.
There are other ETL use cases where users want to change CPU and memory resources between stages, for instance there is data skew or perhaps the data size is much larger in certain stages of the application. In this talk, I will go over the feature details, cluster requirements, the API and use cases. I will demo how the stage level scheduling API can be used by Horovod to seamlessly go from data preparation to training using the Tensorflow Keras API using GPUs.
The talk will also touch on other new Apache Spark 3.1 functionality, such as pluggable caching, which can be used to enable faster dataframe access when operating from GPUs.
Simplify Data Conversion from Spark to TensorFlow and PyTorch
Simplify Data Conversion from Spark to TensorFlow and PyTorchDatabricks In this talk, I would like to introduce an open-source tool built by our team that simplifies the data conversion from Apache Spark to deep learning frameworks.
Imagine you have a large dataset, say 20 GBs, and you want to use it to train a TensorFlow model. Before feeding the data to the model, you need to clean and preprocess your data using Spark. Now you have your dataset in a Spark DataFrame. When it comes to the training part, you may have the problem: How can I convert my Spark DataFrame to some format recognized by my TensorFlow model?
The existing data conversion process can be tedious. For example, to convert an Apache Spark DataFrame to a TensorFlow Dataset file format, you need to either save the Apache Spark DataFrame on a distributed filesystem in parquet format and load the converted data with third-party tools such as Petastorm, or save it directly in TFRecord files with spark-tensorflow-connector and load it back using TFRecordDataset. Both approaches take more than 20 lines of code to manage the intermediate data files, rely on different parsing syntax, and require extra attention for handling vector columns in the Spark DataFrames. In short, all these engineering frictions greatly reduced the data scientists’ productivity.
The Databricks Machine Learning team contributed a new Spark Dataset Converter API to Petastorm to simplify these tedious data conversion process steps. With the new API, it takes a few lines of code to convert a Spark DataFrame to a TensorFlow Dataset or a PyTorch DataLoader with default parameters.
In the talk, I will use an example to show how to use the Spark Dataset Converter to train a Tensorflow model and how simple it is to go from single-node training to distributed training on Databricks.
Scaling your Data Pipelines with Apache Spark on Kubernetes
Scaling your Data Pipelines with Apache Spark on KubernetesDatabricks There is no doubt Kubernetes has emerged as the next generation of cloud native infrastructure to support a wide variety of distributed workloads. Apache Spark has evolved to run both Machine Learning and large scale analytics workloads. There is growing interest in running Apache Spark natively on Kubernetes. By combining the flexibility of Kubernetes and scalable data processing with Apache Spark, you can run any data and machine pipelines on this infrastructure while effectively utilizing resources at disposal.
In this talk, Rajesh Thallam and Sougata Biswas will share how to effectively run your Apache Spark applications on Google Kubernetes Engine (GKE) and Google Cloud Dataproc, orchestrate the data and machine learning pipelines with managed Apache Airflow on GKE (Google Cloud Composer). Following topics will be covered: – Understanding key traits of Apache Spark on Kubernetes- Things to know when running Apache Spark on Kubernetes such as autoscaling- Demonstrate running analytics pipelines on Apache Spark orchestrated with Apache Airflow on Kubernetes cluster.
Scaling and Unifying SciKit Learn and Apache Spark Pipelines
Scaling and Unifying SciKit Learn and Apache Spark PipelinesDatabricks Pipelines have become ubiquitous, as the need for stringing multiple functions to compose applications has gained adoption and popularity. Common pipeline abstractions such as “fit” and “transform” are even shared across divergent platforms such as Python Scikit-Learn and Apache Spark.
Scaling pipelines at the level of simple functions is desirable for many AI applications, however is not directly supported by Ray’s parallelism primitives. In this talk, Raghu will describe a pipeline abstraction that takes advantage of Ray’s compute model to efficiently scale arbitrarily complex pipeline workflows. He will demonstrate how this abstraction cleanly unifies pipeline workflows across multiple platforms such as Scikit-Learn and Spark, and achieves nearly optimal scale-out parallelism on pipelined computations.
Attendees will learn how pipelined workflows can be mapped to Ray’s compute model and how they can both unify and accelerate their pipelines with Ray.
Sawtooth Windows for Feature Aggregations
Sawtooth Windows for Feature AggregationsDatabricks In this talk about zipline, we will introduce a new type of windowing construct called a sawtooth window. We will describe various properties about sawtooth windows that we utilize to achieve online-offline consistency, while still maintaining high-throughput, low-read latency and tunable write latency for serving machine learning features.We will also talk about a simple deployment strategy for correcting feature drift – due operations that are not “abelian groups”, that operate over change data.
Redis + Apache Spark = Swiss Army Knife Meets Kitchen Sink
Redis + Apache Spark = Swiss Army Knife Meets Kitchen SinkDatabricks We want to present multiple anti patterns utilizing Redis in unconventional ways to get the maximum out of Apache Spark.All examples presented are tried and tested in production at Scale at Adobe. The most common integration is spark-redis which interfaces with Redis as a Dataframe backing Store or as an upstream for Structured Streaming. We deviate from the common use cases to explore where Redis can plug gaps while scaling out high throughput applications in Spark.
Niche 1 : Long Running Spark Batch Job – Dispatch New Jobs by polling a Redis Queue
· Why?
o Custom queries on top a table; We load the data once and query N times
· Why not Structured Streaming
· Working Solution using Redis
Niche 2 : Distributed Counters
· Problems with Spark Accumulators
· Utilize Redis Hashes as distributed counters
· Precautions for retries and speculative execution
· Pipelining to improve performance
Re-imagine Data Monitoring with whylogs and Spark
Re-imagine Data Monitoring with whylogs and SparkDatabricks In the era of microservices, decentralized ML architectures and complex data pipelines, data quality has become a bigger challenge than ever. When data is involved in complex business processes and decisions, bad data can, and will, affect the bottom line. As a result, ensuring data quality across the entire ML pipeline is both costly, and cumbersome while data monitoring is often fragmented and performed ad hoc. To address these challenges, we built whylogs, an open source standard for data logging. It is a lightweight data profiling library that enables end-to-end data profiling across the entire software stack. The library implements a language and platform agnostic approach to data quality and data monitoring. It can work with different modes of data operations, including streaming, batch and IoT data.
In this talk, we will provide an overview of the whylogs architecture, including its lightweight statistical data collection approach and various integrations. We will demonstrate how the whylogs integration with Apache Spark achieves large scale data profiling, and we will show how users can apply this integration into existing data and ML pipelines.
Raven: End-to-end Optimization of ML Prediction Queries
Raven: End-to-end Optimization of ML Prediction QueriesDatabricks Machine learning (ML) models are typically part of prediction queries that consist of a data processing part (e.g., for joining, filtering, cleaning, featurization) and an ML part invoking one or more trained models. In this presentation, we identify significant and unexplored opportunities for optimization. To the best of our knowledge, this is the first effort to look at prediction queries holistically, optimizing across both the ML and SQL components.
We will present Raven, an end-to-end optimizer for prediction queries. Raven relies on a unified intermediate representation that captures both data processing and ML operators in a single graph structure.
This allows us to introduce optimization rules that
(i) reduce unnecessary computations by passing information between the data processing and ML operators
(ii) leverage operator transformations (e.g., turning a decision tree to a SQL expression or an equivalent neural network) to map operators to the right execution engine, and
(iii) integrate compiler techniques to take advantage of the most efficient hardware backend (e.g., CPU, GPU) for each operator.
We have implemented Raven as an extension to Spark’s Catalyst optimizer to enable the optimization of SparkSQL prediction queries. Our implementation also allows the optimization of prediction queries in SQL Server. As we will show, Raven is capable of improving prediction query performance on Apache Spark and SQL Server by up to 13.1x and 330x, respectively. For complex models, where GPU acceleration is beneficial, Raven provides up to 8x speedup compared to state-of-the-art systems. As part of the presentation, we will also give a demo showcasing Raven in action.
Processing Large Datasets for ADAS Applications using Apache Spark
Processing Large Datasets for ADAS Applications using Apache SparkDatabricks Semantic segmentation is the classification of every pixel in an image/video. The segmentation partitions a digital image into multiple objects to simplify/change the representation of the image into something that is more meaningful and easier to analyze [1][2]. The technique has a wide variety of applications ranging from perception in autonomous driving scenarios to cancer cell segmentation for medical diagnosis.
Exponential growth in the datasets that require such segmentation is driven by improvements in the accuracy and quality of the sensors generating the data extending to 3D point cloud data. This growth is further compounded by exponential advances in cloud technologies enabling the storage and compute available for such applications. The need for semantically segmented datasets is a key requirement to improve the accuracy of inference engines that are built upon them.
Streamlining the accuracy and efficiency of these systems directly affects the value of the business outcome for organizations that are developing such functionalities as a part of their AI strategy.
This presentation details workflows for labeling, preprocessing, modeling, and evaluating performance/accuracy. Scientists and engineers leverage domain-specific features/tools that support the entire workflow from labeling the ground truth, handling data from a wide variety of sources/formats, developing models and finally deploying these models. Users can scale their deployments optimally on GPU-based cloud infrastructure to build accelerated training and inference pipelines while working with big datasets. These environments are optimized for engineers to develop such functionality with ease and then scale against large datasets with Spark-based clusters on the cloud.
Massive Data Processing in Adobe Using Delta Lake
Massive Data Processing in Adobe Using Delta LakeDatabricks At Adobe Experience Platform, we ingest TBs of data every day and manage PBs of data for our customers as part of the Unified Profile Offering. At the heart of this is a bunch of complex ingestion of a mix of normalized and denormalized data with various linkage scenarios power by a central Identity Linking Graph. This helps power various marketing scenarios that are activated in multiple platforms and channels like email, advertisements etc. We will go over how we built a cost effective and scalable data pipeline using Apache Spark and Delta Lake and share our experiences.
What are we storing?
Multi Source – Multi Channel Problem
Data Representation and Nested Schema Evolution
Performance Trade Offs with Various formats
Go over anti-patterns used
(String FTW)
Data Manipulation using UDFs
Writer Worries and How to Wipe them Away
Staging Tables FTW
Datalake Replication Lag Tracking
Performance Time!
Ad
Recently uploaded (20)
apidays New York 2025 - Two tales of API Change Management by Eric Koleda (Coda)
apidays New York 2025 - Two tales of API Change Management by Eric Koleda (Coda)apidays Two tales of API Change Management from my time at Google
Eric Koleda, Developer Advocate at Coda
apidays New York 2025
API Management for Surfing the Next Innovation Waves: GenAI and Open Banking
Convene 360 Madison, New York
May 14 & 15, 2025
------
Check out our conferences at https://www.apidays.global/
Do you want to sponsor or talk at one of our conferences?
https://apidays.typeform.com/to/ILJeAaV8
Learn more on APIscene, the global media made by the community for the community:
https://www.apiscene.io
Explore the API ecosystem with the API Landscape:
https://apilandscape.apiscene.io/
PSUG 7 - 2025-06-03 - David Bianco on Splunk SURGe
PSUG 7 - 2025-06-03 - David Bianco on Splunk SURGeTomas Moser Meet David Bianco, Staff Strategist with Splunk’s elite SURGe team, live in Prague. Get ready for an engaging deep dive into the cutting edge of cybersecurity—straight from the experts driving Splunk’s global security research.
apidays New York 2025 - Spring Modulith Design for Microservices by Renjith R...
apidays New York 2025 - Spring Modulith Design for Microservices by Renjith R...apidays Spring Modulith Design for Microservices
Renjith Ramachandran, Senior Solutions Architect at BJS Wholesale Club
apidays New York 2025
API Management for Surfing the Next Innovation Waves: GenAI and Open Banking
Convene 360 Madison, New York
May 14 & 15, 2025
------
Check out our conferences at https://www.apidays.global/
Do you want to sponsor or talk at one of our conferences?
https://apidays.typeform.com/to/ILJeAaV8
Learn more on APIscene, the global media made by the community for the community:
https://www.apiscene.io
Explore the API ecosystem with the API Landscape:
https://apilandscape.apiscene.io/
THE FRIEDMAN TEST ( Biostatics B. Pharm)
THE FRIEDMAN TEST ( Biostatics B. Pharm)JishuHaldar The Friedman Test is a valuable non-parametric alternative to the
Repeated Measures ANOVA, allowing for the comparison of three or
more related groups when data is ordinal or not normally distributed.
By ranking data instead of using raw values, the test overcomes the
limitations of parametric tests, making it ideal for small sample sizes and
real-world applications in medicine, psychology, pharmaceutical
sciences, and education. However, while it effectively detects differences
among groups, it does not indicate which specific groups differ, requiring
further post-hoc analysis.
apidays New York 2025 - The FINOS Common Domain Model for Capital Markets by ...
apidays New York 2025 - The FINOS Common Domain Model for Capital Markets by ...apidays The FINOS Common Domain Model for Capital Markets
Tom Healey, Founder & Director at FINXIS LLC
Daniel Schwartz, Managing Partner at FT Advisory LLC
apidays New York 2025
API Management for Surfing the Next Innovation Waves: GenAI and Open Banking
May 14 & 15, 2025
------
Check out our conferences at https://www.apidays.global/
Do you want to sponsor or talk at one of our conferences?
https://apidays.typeform.com/to/ILJeAaV8
Learn more on APIscene, the global media made by the community for the community:
https://www.apiscene.io
Explore the API ecosystem with the API Landscape:
https://apilandscape.apiscene.io/
AG-FIRMA FINCOME ARTICLE AI AGENT RAG.pdf
AG-FIRMA FINCOME ARTICLE AI AGENT RAG.pdfAnass Nabil AI CHAT BOT Design of a multilingual AI assistant to optimize agricultural practices in Morocco
Delivery service status checking
Mobile architecture + orchestrator LLM + expert agents (RAG, weather,sensors).
apidays New York 2025 - Why an SDK is Needed to Protect APIs from Mobile Apps...
apidays New York 2025 - Why an SDK is Needed to Protect APIs from Mobile Apps...apidays Why an SDK is Needed to Protect APIs from Mobile Apps
Pearce Erensel, Global VP of Sales at Approov Mobile Security
apidays New York 2025
API Management for Surfing the Next Innovation Waves: GenAI and Open Banking
May 14 & 15, 2025
------
Check out our conferences at https://www.apidays.global/
Do you want to sponsor or talk at one of our conferences?
https://apidays.typeform.com/to/ILJeAaV8
Learn more on APIscene, the global media made by the community for the community:
https://www.apiscene.io
Explore the API ecosystem with the API Landscape:
https://apilandscape.apiscene.io/
apidays New York 2025 - Lessons From Two Technical Transformations by Leah Hu...
apidays New York 2025 - Lessons From Two Technical Transformations by Leah Hu...apidays You Can't Outrun Complexity - But You Can Orchestrate It: Lessons From Two Technical Transformations
Leah Hurwich Adler, Senior Staff Product Manager at Apollo GraphQL
apidays New York 2025
API Management for Surfing the Next Innovation Waves: GenAI and Open Banking
May 14 & 15, 2025
------
Check out our conferences at https://www.apidays.global/
Do you want to sponsor or talk at one of our conferences?
https://apidays.typeform.com/to/ILJeAaV8
Learn more on APIscene, the global media made by the community for the community:
https://www.apiscene.io
Explore the API ecosystem with the API Landscape:
https://apilandscape.apiscene.io/
delta airlines new york office (Airwayscityoffice)
delta airlines new york office (Airwayscityoffice)jamespromind Visit the Delta Airlines New York Office for personalized assistance with your travel plans. The experienced team offers guidance on ticket changes, flight delays, and more. It’s a helpful resource for those needing support beyond the airport.
原版英国威尔士三一圣大卫大学毕业证(UWTSD毕业证书)如何办理
原版英国威尔士三一圣大卫大学毕业证(UWTSD毕业证书)如何办理Taqyea 学校原版文凭补办(UWTSD毕业证书)威尔士三一圣大卫大学毕业证购买毕业证【q微1954292140】威尔士三一圣大卫大学offer/学位证、留信官方学历认证（永久存档真实可查）采用学校原版纸张、特殊工艺完全按照原版一比一制作【q微1954292140】Buy University of Wales Trinity Saint David Diploma购买美国毕业证，购买英国毕业证，购买澳洲毕业证，购买加拿大毕业证，以及德国毕业证，购买法国毕业证（q微1954292140）购买荷兰毕业证、购买瑞士毕业证、购买日本毕业证、购买韩国毕业证、购买新西兰毕业证、购买新加坡毕业证、购买西班牙毕业证、购买马来西亚毕业证等。包括了本科毕业证，硕士毕业证。
主营项目：
1、真实教育部国外学历学位认证《英国毕业文凭证书快速办理威尔士三一圣大卫大学学位证书成绩单代办服务》【q微1954292140】《论文没过威尔士三一圣大卫大学正式成绩单》，教育部存档，教育部留服网站100%可查.
2、办理UWTSD毕业证，改成绩单《UWTSD毕业证明办理威尔士三一圣大卫大学文凭认证》【Q/WeChat：1954292140】Buy University of Wales Trinity Saint David Certificates《正式成绩单论文没过》，威尔士三一圣大卫大学Offer、在读证明、学生卡、信封、证明信等全套材料，从防伪到印刷，从水印到钢印烫金，高精仿度跟学校原版100%相同.
3、真实使馆认证（即留学人员回国证明），使馆存档可通过大使馆查询确认.
4、留信网认证，国家专业人才认证中心颁发入库证书，留信网存档可查.
英国威尔士三一圣大卫大学毕业证(UWTSD毕业证书）UWTSD文凭【q微1954292140】高仿真还原英国文凭证书和外壳，定制英国威尔士三一圣大卫大学成绩单和信封。研究生学历信息UWTSD毕业证【q微1954292140】文凭详解细节威尔士三一圣大卫大学offer/学位证英国毕业证、留信官方学历认证（永久存档真实可查）采用学校原版纸张、特殊工艺完全按照原版一比一制作。帮你解决威尔士三一圣大卫大学学历学位认证难题。
【办理威尔士三一圣大卫大学成绩单Buy University of Wales Trinity Saint David Transcripts】
购买日韩成绩单、英国大学成绩单、美国大学成绩单、澳洲大学成绩单、加拿大大学成绩单（q微1954292140）新加坡大学成绩单、新西兰大学成绩单、爱尔兰成绩单、西班牙成绩单、德国成绩单。成绩单的意义主要体现在证明学习能力、评估学术背景、展示综合素质、提高录取率，以及是作为留信认证申请材料的一部分。
威尔士三一圣大卫大学成绩单能够体现您的的学习能力，包括威尔士三一圣大卫大学课程成绩、专业能力、研究能力。（q微1954292140）具体来说，成绩报告单通常包含学生的学习技能与习惯、各科成绩以及老师评语等部分，因此，成绩单不仅是学生学术能力的证明，也是评估学生是否适合某个教育项目的重要依据！
Buy University of Wales Trinity Saint David Diploma《正式成绩单论文没过》有文凭却得不到认证。又该怎么办？？？英国毕业证购买，英国文凭购买，【q微1954292140】英国文凭购买，英国文凭定制，英国文凭补办。专业在线定制英国大学文凭，定做英国本科文凭，【q微1954292140】复制英国University of Wales Trinity Saint David completion letter。在线快速补办英国本科毕业证、硕士文凭证书，购买英国学位证、威尔士三一圣大卫大学Offer，英国大学文凭在线购买。
特殊原因导致无法毕业，也可以联系我们帮您办理相关材料：
１：在威尔士三一圣大卫大学挂科了，不想读了，成绩不理想怎么办？
2：打算回国了，找工作的时候，需要提供认证《UWTSD成绩单购买办理威尔士三一圣大卫大学毕业证书范本》
帮您解决在英国威尔士三一圣大卫大学未毕业难题（University of Wales Trinity Saint David）文凭购买、毕业证购买、大学文凭购买、大学毕业证购买、买文凭、日韩文凭、英国大学文凭、美国大学文凭、澳洲大学文凭、加拿大大学文凭（q微1954292140）新加坡大学文凭、新西兰大学文凭、爱尔兰文凭、西班牙文凭、德国文凭、教育部认证，买毕业证，毕业证购买，买大学文凭，【q微1954292140】学位证1:1完美还原海外各大学毕业材料上的工艺：水印，阴影底纹，钢印LOGO烫金烫银，LOGO烫金烫银复合重叠。文字图案浮雕、激光镭射、紫外荧光、温感、复印防伪等防伪工艺。《威尔士三一圣大卫大学扫描件文凭定做英国毕业证书办理UWTSD购买毕业证》
购买日韩毕业证、英国大学毕业证、美国大学毕业证、澳洲大学毕业证、加拿大大学毕业证（q微1954292140）新加坡大学毕业证、新西兰大学毕业证、爱尔兰毕业证、西班牙毕业证、德国毕业证，回国证明，留信网认证，留信认证办理，学历认证。从而完成就业。威尔士三一圣大卫大学毕业证办理，威尔士三一圣大卫大学文凭办理，威尔士三一圣大卫大学成绩单办理和真实留信认证、留服认证、威尔士三一圣大卫大学学历认证。学院文凭定制，威尔士三一圣大卫大学原版文凭补办，成绩单如何办理，扫描件文凭定做，100%文凭复刻。
apidays New York 2025 - Unifying OpenAPI & AsyncAPI by Naresh Jain & Hari Kri...
apidays New York 2025 - Unifying OpenAPI & AsyncAPI by Naresh Jain & Hari Kri...apidays Unifying OpenAPI & AsyncAPI: Designing JSON Schemas+Examples for Reuse
Naresh Jain, Co-founder & CEO at Specmatic
Hari Krishnan, Co-founder & CTO at Specmatic
apidays New York 2025
API Management for Surfing the Next Innovation Waves: GenAI and Open Banking
May 14 & 15, 2025
------
Check out our conferences at https://www.apidays.global/
Do you want to sponsor or talk at one of our conferences?
https://apidays.typeform.com/to/ILJeAaV8
Learn more on APIscene, the global media made by the community for the community:
https://www.apiscene.io
Explore the API ecosystem with the API Landscape:
https://apilandscape.apiscene.io/
MICROSOFT POWERPOINT AND USES(BEST)..pdf
MICROSOFT POWERPOINT AND USES(BEST)..pdfbathyates Talks about presentation packages and their uses to man and how it functions being the best presentation package. Learn about presentation packages here with me
Materialized Column: An Efficient Way to Optimize Queries on Nested Columns
- 1. Materialized Column——An Efficient Way to Optimize Queries on Nested Columns Guo, Jun ([email protected]) Lead of Data Engine Team, @ByteDance
- 2. Who we are o Data Engine team of ByteDance o Build a platform of one-stop experience for OLAP , on which users can analyze PB level data by writing SQL without caring about the underlying execution engine
- 3. What we do o Manage Spark SQL / Presto / Hive workload o Offer Open API and self-serve platform o Optimize Spark SQL / Presto / Hive engine o Design data architecture for most business lines in ByteDance
- 4. Agenda ▪ Spark SQL at ByteDance ▪ Why nested type are widely used ▪ What are the main issues of nested type ▪ Optional solutions ▪ How does Materialized Column solve these problems
- 5. Spark SQL at ByteDance
- 6. Spark SQL at ByteDance 2016 2017 2018 2019 2020 Small Scale Experiments Ad-hoc workload Few ETL pipelines in production Full-production deployment Main engine in DW area
- 7. Why nested type are widely used
- 8. Why nested type are widely used ▪ Event log ▪ A lot of new tracking events are created everyday ▪ It is not a good idea to create a new column for a new type of event ▪ Dimension ▪ Dimension tables are dumped from MySQL of service backend ▪ Service backend may add some new fields on demand. These fields may not be helpful for now but they may be useful in the future
- 9. Main issues for nested type
- 10. Main issues for nested type ▪ Unnecessary data are read which is a waste of IO ▪ Vectorized read can not be exploit when nested type column is read ▪ Filter pushdown can not be utilized when nested column is read ▪ Duplicated computation. e.g. JSON parsing is CPU-intensive
- 12. Optional solutions – A separate table ▪ DW users design a solution to solve these problems ▪ Maintain a new table which add new columns which are extracted from the nested columns ▪ Downstream users should query on this new table and new columns for better performance
- 13. Optional solutions – A separate table ▪ Pros ▪ Queries are on simple type so that all the problems are solved ▪ Cons ▪ Need to push all the downstream users to migrate their queries / pipelines to the new table and new columns ▪ Duplicated storage and computation cost ▪ Can not handle frequent subfields changing
- 14. Optional solutions – Vectorized Read on Nested Column ▪ Refactor Parquet vectorized reader to support vectorized read for nested types ▪ Support predicate pushdown for struct
- 15. Optional solutions – Vectorized Read on Nested Column ▪ Pros ▪ Enable vectorized read without any storage overhead ▪ Cons ▪ Need to refactor vectorized reader for Parquet and ORC respectively ▪ Filter pushdown for Array/Map is still not available ▪ The performance of vectorized read on nested type is not as good as that for simple type ▪ Improve performance with struct by about 100% ▪ Improve performance with map by about 163%
- 16. How does Materialized Column solve these problems
- 17. How does Materialized Column solve these problems CREATE TABLE base_table ( item STRING, count INT, people<STRING, STRING> date STRING ) USING parquet PARTITIONED BY (date); ALTER TABLE base_table ADD COLUMNS ( age INT MATERIALIZED CAST(peopl e[‘age’] AS INTEGER) ); Add materialized columnOriginal table
- 18. How does Materialized Column solve these problems
- 19. How does Materialized Column solve these problems Write with materialized column explain extended insert into base_table partition(date='20201010') select 'appole', 1, map('age','18','name','jack','gender','male')
- 20. How does Materialized Column solve these problems Query with materialized column rewriteQuery without materialized column rewrite
- 21. How does Materialized Column solve these problems Test case Without Materialized Column rewrite With Materialized Column rewrite Performance Read data size SQL_adhoc_1 6.3 min / 797.6 GB 3.4 min / 111.8 GB 85.3%↑ 86% ↓ SQL_adhoc_2 16.5 min / 3.2 TB 5.0 min / 111.1 GB 230%↑ 96.6%↓ SQL_etl_1 24 min / 3.7 TB 9.1 min / 686.1 GB 130.8%↑ 82%↓ Query without materialized column rewrite
- 22. Feedback Your feedback is important to us. Don’t forget to rate and review the sessions.