Jeremy Beard, a senior solutions architect at Cloudera, introduces Kudu, a new column-oriented storage system for Apache Hadoop designed for fast analytics on fast changing data. Kudu is meant to fill gaps in HDFS and HBase by providing efficient scanning, finding and writing capabilities simultaneously. It uses a relational data model with ACID transactions and integrates with common Hadoop tools like Impala, Spark and MapReduce. Kudu aims to simplify real-time analytics use cases by allowing data to be directly updated without complex ETL processes.

1. 1© Cloudera, Inc. All rights reserved.
Introducing Kudu
Jeremy Beard | Senior Solutions Architect
December 2015

2. 2© Cloudera, Inc. All rights reserved.
Presenter
• Jeremy Beard
• Senior Solutions Architect at Cloudera
• Three years in big data
• Six years in data warehousing
• jeremy@cloudera.com

3. 3© Cloudera, Inc. All rights reserved.
Current storage landscape in Hadoop
HDFS excels at:
• Efficiently scanning large amounts
of data
• Accumulating data with high
throughput
HBase excels at:
• Efficiently finding and writing
individual rows
• Making data mutable
Gaps exist when these properties
are needed simultaneously

4. 4© Cloudera, Inc. All rights reserved.
Changing hardware landscape
• Spinning disk -> solid state storage
• NAND flash: Up to 450k read 250k write iops, about 2GB/sec read and
1.5GB/sec write throughput, at a price of less than $3/GB and dropping
• 3D XPoint memory (1000x faster than NAND, cheaper than RAM)
• RAM is cheaper and more abundant:
• 64->128->256GB over last few years
• Takeaway 1: The next bottleneck is CPU, and current storage systems weren’t
designed with CPU efficiency in mind
• Takeaway 2: Column stores are feasible for random access

5. 5© Cloudera, Inc. All rights reserved.
Kudu
Storage for Fast Analytics on Fast Data
• New updating column store for Hadoop
• Simplifies the architecture for building analytic
applications on changing data
• Designed for fast analytic performance
• Natively integrated with Hadoop
• Donated as incubating project at
Apache Software Foundation
• Beta now available
STRUCTURED
Sqoop
UNSTRUCTURED
Kafka, Flume
PROCESS, ANALYZE, SERVE
UNIFIED SERVICES
RESOURCE MANAGEMENT
YARN
SECURITY
Sentry, RecordService
FILESYSTEM
HDFS
RELATIONAL
Kudu
NoSQL
HBase
STORE
INTEGRATE
BATCH
Spark, Hive, Pig
MapReduce
STREAM
Spark
SQL
Impala
SEARCH
Solr
SDK
Kite

6. 6© Cloudera, Inc. All rights reserved.
• High throughput for big scans (columnar
storage and replication)
Goal: Within 2x of Parquet
• Low-latency for short accesses (primary key
indexes and quorum design)
Goal: 1ms read/write on SSD
• Database-like semantics (initially single-row
ACID)
• Relational data model
• SQL query
• “NoSQL” style scan/insert/update (Java client)
Kudu design goals

7. 7© Cloudera, Inc. All rights reserved.
Kudu basic design
• Apache-licensed open source software
• Structured data model
• Basic construct: tables
• Tables broken down into tablets (roughly equivalent to partitions)
• Architecture supports geographically disparate, active/active systems
• Not the initial design goal

8. 8© Cloudera, Inc. All rights reserved.
What Kudu is not
• Not a SQL interface
• Just the storage layer
• “BYO SQL”
• Not a file system
• Data must have tabular structure
• Not an application that runs on HDFS
• An alternative, native Hadoop storage engine
• Not a replacement for HDFS or HBase
• Select the right storage for the right use case
• Cloudera will continue to support and invest in all three

9. 9© Cloudera, Inc. All rights reserved.
Kudu data model
• Tables have a RDBMS-like schema
• Finite number of columns (unlike HBase/Cassandra)
• Types: BOOL, INT8/16/32/64, FLOAT, DOUBLE, STRING, BINARY, TIMESTAMP
• Some subset of columns makes up a primary key
• Fast random reads/writes by primary key
• No secondary indexes (yet)
• Columnar layout on disk
• Lazy materialization
• Encoding and compression options
9

10. 10© Cloudera, Inc. All rights reserved.
Table partitioning
• Hash bucketing
• Distribute records by hash of partition column(s)
• N buckets leads to N tablets
• Range partitioning
• Distribute records by ranges of the partition column(s)
• N split keys leads to N tablets
• Can be a mix for different columns of the primary key

11. 11© Cloudera, Inc. All rights reserved.
Consistency model
• Consistency and replication enforced by Raft consensus (similar to Paxos)
• Replication by operation not data
• Single-row transactions now
• Multi-row transactions later
• Geo-distributed replicas will be possible under strict time synchronization
• Techniques drawn from Google Spanner and others

12. 12© Cloudera, Inc. All rights reserved.
Kudu interfaces
• NoSQL-style APIs
• Insert(), Update(), Delete(), Scan()
• Java and C++ now
• Python soon
• Integrations with MapReduce, Spark, and Impala
• No direct access to underlying Kudu tablet files
• Beta does not have authentication, authorization, encryption

13. 13© Cloudera, Inc. All rights reserved.
Impala integration
• Opens up Kudu to JDBC/ODBC clients
• Intuitive way to get data into Kudu
• INSERT INTO kudu SELECT * FROM csv;
• Additional commands
• UPDATE
• DELETE
• Efficient INSERT VALUES
• Runs on the Kudu C++ client

14. 14© Cloudera, Inc. All rights reserved.
Performance characteristics
• Very CPU efficient
• Written in modern C++, uses specialized CPU instructions, JIT compilation
• Latency mostly driven by storage hardware capabilities
• Expect sub-millisecond response on SSDs and upcoming technologies
• No garbage collection allows very large memory footprint with no pauses
• Bloom filters reduce the need for many disk accesses

15. 15© Cloudera, Inc. All rights reserved.
Operating Kudu
• Easiest through Cloudera Manager integration
• Separate parcel for now
• Kudu is always compacting
• No minor vs. major compaction
• No compaction latency spikes
• Web UI is full of metrics and logs

16. 16© Cloudera, Inc. All rights reserved.
Cluster layout
• One or multiple masters
• Only one in current beta
• Low CPU and memory impact
• One tablet server per worker node
• Can share disks with HDFS
• One SSD per worker node just for Kudu WAL can speed up writes
• No dependencies on other Hadoop ecosystem components
• But interfacing components like Impala or Spark do

17. 17© Cloudera, Inc. All rights reserved.
Real-time analytics in Hadoop today
Merging in new data = storage complexity
Downsides:
● Multiple storage layers
● Latest data is hidden
● Files are messy
● Complex to do updates
without breaking running
queriesNew Partition
Most Recent Partition
Historic Data
HBase
Parquet
File
Have we
accumulated
enough data?
Reorganize
HBase file
into Parquet
• Wait for running operations to complete
• Define new Impala partition referencing
the newly written Parquet file
Incoming Data
(Messaging
System)
Reporting
Request
HDFS + Impala

18. 18© Cloudera, Inc. All rights reserved.
Real-time analytics in Hadoop with Kudu
Improvements:
● One system to operate
● No schedules or
background processes
● Handle late arrivals or data
corrections with ease
● New data available
immediately for analytics
or operations
Historical and Real-time
Data
Incoming Data
(Messaging
System)
Reporting
Request
Kudu + Impala

19. 19© Cloudera, Inc. All rights reserved.
Kudu for data warehousing
• Near real time data visibility
• BI tools can display events that happened seconds earlier
• Excellent for star schemas
• Fast scans of deep fact tables
• Efficient wide fact tables
• Simplified updates of slowly changing dimensions

20. 20© Cloudera, Inc. All rights reserved.
Near real time data warehousing on Kudu
Files
RDBMS
Streams
K
A
F
K
A
K
U
D
U
IMPALA
HUE
BI tools
User
FLUME
SPARK
STREAMING
Simple
Complex

21. 21© Cloudera, Inc. All rights reserved.
Resources
Join the community
http://getkudu.io
kudu-user@googlegroups.com
Download the beta
cloudera.com/downloads
Read the whitepaper
getkudu.io/kudu.pdf

22. 22© Cloudera, Inc. All rights reserved.
Thank you
jeremy@cloudera.com