This document discusses Apache Drill, an open source SQL query engine for analysis of large scale datasets across various data sources like Hadoop, HBase etc. It provides interactive queries on large datasets with low latency. The document explains Drill's architecture, data model, query processing, extensibility features and how it integrates with Hadoop ecosystem. It encourages readers to get involved with the Apache Drill community.

1. 1©MapR Technologies - Confidential
Apache Drill

2. 2©MapR Technologies - Confidential
My Background
 Academia, Startups
– Aptex, MusicMatch, ID Analytics, Veoh
– Big data since before big
 Open source
– since the dark ages before the internet
– Mahout, Zookeeper, Drill
– bought the beer at first HUG
 MapR
 Founding member of Apache Drill

3. 3©MapR Technologies - Confidential
MapR Technologies
 The open enterprise-grade distribution for Hadoop
– Easy, dependable and fast
– Open source with standards-based extensions
 MapR is deployed at 1000’s of companies
– From small Internet startups to the world’s largest enterprises
 MapR customers analyze massive amounts of data:
– Hundreds of billions of events daily
– 90% of the world’s Internet population monthly
– $1 trillion in retail purchases annually
 MapR has partnered with Google to provide Hadoop on Google Compute
Engine

4. 4©MapR Technologies - Confidential
Agenda
 What?
– What exactly does Drill do?
 Why?
– Why do we need Apache Drill?
 Who?
– Who is doing this?
 How?
– How does Drill work inside?
 Conclusion
– How can you help?
– Where can you find out more?

5. 5©MapR Technologies - Confidential
Apache Drill Overview
 Drill overview
– Low latency interactive queries
– Standard ANSI SQL support
 Open-Source
– 100’s involved across US and Europe
– Community consensus on API, functionality
 PMC expects first version late this quarter
– Several components already developed

6. 6©MapR Technologies - Confidential
Big Data Processing – Hadoop
Batch processing
Query runtime Minutes to hours
Data volume TBs to PBs
Programming
model
MapReduce
Users Developers
Google project MapReduce
Open source
project
Hadoop
MapReduce

7. 7©MapR Technologies - Confidential
Big Data Processing – Hadoop and Storm
Batch processing Stream processing
Query runtime Minutes to hours Never-ending
Data volume TBs to PBs Continuous stream
Programming
model
MapReduce DAG
(pre-programmed)
Users Developers Developers
Google project MapReduce
Open source
project
Hadoop
MapReduce
Storm or Apache S4

8. 8©MapR Technologies - Confidential
Big Data Processing – The missing part
Batch processing Interactive analysis Stream processing
Query runtime Minutes to hours Never-ending
Data volume TBs to PBs Continuous stream
Programming
model
MapReduce DAG
(pre-programmed)
Users Developers Developers
Google project MapReduce
Open source
project
Hadoop
MapReduce
Storm and S4

9. 9©MapR Technologies - Confidential
Big Data Processing – The missing part
Batch processing Interactive analysis Stream processing
Query runtime Minutes to hours Milliseconds to
minutes
Never-ending
Data volume TBs to PBs GBs to PBs Continuous stream
Programming
model
MapReduce Queries
(ad hoc)
DAG
(pre-programmed)
Users Developers Analysts and
developers
Developers
Google project MapReduce
Open source
project
Hadoop
MapReduce
Storm and S4

10. 10©MapR Technologies - Confidential
Big Data Processing
Batch processing Interactive analysis Stream processing
Query runtime Minutes to hours Milliseconds to
minutes
Never-ending
Data volume TBs to PBs GBs to PBs Continuous stream
Programming
model
MapReduce Queries DAG
Users Developers Analysts and
developers
Developers
Google project MapReduce Dremel
Open source
project
Hadoop
MapReduce
Storm and S4

11. 11©MapR Technologies - Confidential
Big Data Processing
Batch processing Interactive analysis Stream processing
Query runtime Minutes to hours Milliseconds to
minutes
Never-ending
Data volume TBs to PBs GBs to PBs Continuous stream
Programming
model
MapReduce Queries DAG
Users Developers Analysts and
developers
Developers
Google project MapReduce Dremel
Open source
project
Hadoop
MapReduce
Storm and S4
Introducing Apache Drill

12. 12©MapR Technologies - Confidential
Latency Matters
 Ad-hoc analysis with interactive tools
 Real-time dashboards
 Event/trend detection and analysis
– Network intrusions
– Fraud
– Failures

13. 13©MapR Technologies - Confidential
Nested Query Languages
 DrQL
– SQL-like query language for nested data
– Compatible with Google BigQuery/Dremel
• BigQuery applications should work with Drill
– Designed to support efficient column-based processing
• No record assembly during query processing
 Mongo Query Language
– {$query: {x: 3, y: "abc"}, $orderby: {x: 1}}
 Other languages/programming models can plug in

14. 14©MapR Technologies - Confidential
Nested Data Model
 The data model in Dremel is Protocol Buffers
– Nested
– Schema
 Apache Drill is designed to support multiple data models
– Schema: Protocol Buffers, Apache Avro, …
– Schema-less: JSON, BSON, …
 Flat records are supported as a special case of nested data
– CSV, TSV, …
{
"name": "Srivas",
"gender": "Male",
"followers": 100
}
{
"name": "Raina",
"gender": "Female",
"followers": 200,
"zip": "94305"
}
enum Gender {
MALE, FEMALE
}
record User {
string name;
Gender gender;
long followers;
}
Avro IDL JSON

15. 15©MapR Technologies - Confidential
Extensibility
 Nested query languages
– Pluggable model
– DrQL
– Mongo Query Language
– Cascading
 Distributed execution engine
– Extensible model (eg, Dryad)
– Low-latency
– Fault tolerant
 Nested data formats
– Pluggable model
– Column-based (ColumnIO/Dremel, Trevni, RCFile) and row-based (RecordIO, Avro, JSON, CSV)
– Schema (Protocol Buffers, Avro, CSV) and schema-less (JSON, BSON)
 Scalable data sources
– Pluggable model
– Hadoop
– HBase

16. 16©MapR Technologies - Confidential
Design Principles
Flexible
• Pluggable query languages
• Extensible execution engine
• Pluggable data formats
• Column-based and row-based
• Schema and schema-less
• Pluggable data sources
Easy
• Unzip and run
• Zero configuration
• Reverse DNS not needed
• IP addresses can change
• Clear and concise log messages
Dependable
• No SPOF
• Instant recovery from crashes
Fast
• C/C++ core with Java support
• Google C++ style guide
• Min latency and max throughput
(limited only by hardware)

17. 17©MapR Technologies - Confidential
Apache DRill

18. 18©MapR Technologies - Confidential
Architecture
 Only the execution engine knows the physical attributes of the cluster
– # nodes, hardware, file locations, …
 Public interfaces enable extensibility
– Developers can build parsers for new query languages
– Developers can provide an execution plan directly
 Each level of the plan has a human readable representation
– Facilitates debugging and unit testing

19. 19©MapR Technologies - Confidential
Execution Engine Layers
 Drill execution engine has two layers
– Operator layer is serialization-aware
• Processes individual records
– Execution layer is not serialization-aware
• Processes batches of records (blobs)
• Responsible for communication, dependencies and fault tolerance

20. 20©MapR Technologies - Confidential
DrQL Example
SELECT DocId AS Id,
COUNT(Name.Language.Code) WITHIN Name AS
Cnt,
Name.Url + ',' + Name.Language.Code AS
Str
FROM t
WHERE REGEXP(Name.Url, '^http')
AND DocId < 20;
* Example from the Dremel paper

21. 21©MapR Technologies - Confidential
Query Components
 Query components:
– SELECT
– FROM
– WHERE
– GROUP BY
– HAVING
– (JOIN)
 Key logical operators:
– Scan
– Filter
– Aggregate
– (Join)

22. 22©MapR Technologies - Confidential
scan-json
filter
flatten
aggregate
exp1
exp2
"table-1"
Logical Plan

23. 23©MapR Technologies - Confidential
Execution Plan
scan-json
filter
flatten
aggregate
exp1
exp2
"table-1" scan-json
filter
flatten
exp1
"table-1" scan-json
filter
flatten
exp1
"table-1"
node1 node2 node3

24. 24©MapR Technologies - Confidential
{op: "sequence",
do: [
{op: "scan",
source: "table-1.json"
selection: "*"
},
{op: "filter",
expr: <expr>
},
{op: "flatten",
expr: <expr>,
drop: "false"
},
{op: "aggregate",
type: repeat,
keys: [<name>,...],
aggregations: [
{ref: <name>, expr: <aggexpr> },...
]
}
]
}
Logical Plan Syntax

25. 25©MapR Technologies - Confidential
Representing a DAG
{ @id: 19, op: "aggregate",
input: 18,
type: <simple|running|repeat>,
keys: [<name>,...],
aggregations: [
{ref: <name>, expr: <aggexpr> },...
]
}
aggregate exp2
18
19

26. 26©MapR Technologies - Confidential
Multiple Inputs
{ @id: 25, op: "cogroup",
groupings: [
{ref: 23, expr: “id”}, {ref:
24, expr: “id”}
]
}
cogroup
23
25
id24id

27. 27©MapR Technologies - Confidential
Scan Operators
Scan with schema Scan without schema
Operator
output
Protocol Buffers JSON-like (MessagePack)
Supported
data formats
ColumnIO (column-based protobuf/Dremel)
RecordIO (row-based protobuf)
CSV
JSON
HBase
SELECT …
FROM …
ColumnIO(proto URI, data URI)
RecordIO(proto URI, data URI)
Json(data URI)
HBase(table name)
• Drill supports multiple data formats by having per-format scan operators
• Queries involving multiple data formats/sources are supported
• Fields and predicates can be pushed down into the scan operator
• Scan operators may have adaptive side-effects (database cracking)
• Produce ColumnIO from RecordIO
• Google PowerDrill stores materialized expressions with the data

28. 28©MapR Technologies - Confidential
Design Principles
Flexible
• Pluggable query languages
• Extensible execution engine
• Pluggable data formats
• Column-based and row-based
• Schema and schema-less
• Pluggable data sources
Easy
• Unzip and run
• Zero configuration
• Reverse DNS not needed
• IP addresses can change
• Clear and concise log messages
Dependable
• No SPOF
• Instant recovery from crashes
Fast
• C/C++ core with Java support
• Google C++ style guide
• Min latency and max throughput
(limited only by hardware)

29. 29©MapR Technologies - Confidential
Hadoop Integration
 Hadoop data sources
– Hadoop FileSystem API (HDFS/MapR-FS)
– HBase
 Hadoop data formats
– Apache Avro
– RCFile
 MapReduce-based tools to create column-based formats
 Table registry in HCatalog
 Run long-running services in YARN

30. 30©MapR Technologies - Confidential
Get Involved!
 Download these slides
– http://www.mapr.com/company/events/hug-france-12-04-2012
 Join the project
– drill-dev-subscribe@incubator.apache.org
– #apachedrill
 Contact me:
– tdunning@maprtech.com
– tdunning@apache.org
– ted.dunning@gmail.com
– @ted_dunning
 Join MapR
– jobs@mapr.com