Gene Pang of Alluxio, Inc presented on Alluxio, an open source project that provides unified access to data across storage systems at memory speed. Alluxio allows data to be accessed locally or from remote Alluxio nodes, accelerating data access by up to 30x for companies like Baidu. It also enables data sharing between jobs and applications at memory speed instead of disk speed, reducing Barclays' workflow iteration time from hours to seconds. Additionally, Alluxio provides a unified namespace to access data from multiple storage systems like S3, HDFS and NFS through a single interface without changing applications. This feature has improved performance by 15x-300x for companies like Qunar.

1. ALLUXIO (FORMERLY TACHYON): UNIFY DATA AT MEMORY SPEED
Global Big Data Conference, San Jose
March 2017
Gene Pang, Alluxio, Inc.

2. HISTORY
• Started at UC Berkeley AMPLab In Summer 2012
• Originally named as Tachyon
• Rebranded to Alluxio in early 2016
• Open Sourced in 2013
• Apache License 2.0
• Latest Stable Release: Alluxio 1.4.0
• Alluxio 1.5.0 Planned For Q2, 2017
2

3. ALLUXIO DEPLOYMENTS
© 2016 Alluxio Confidential 3

4. BIG DATA ECOSYSTEM TODAYBIG DATA ECOSYSTEM WITH ALLUXIO
…
…
FUSE Compatible File SystemHadoop Compatible File System Native Key-Value InterfaceNative File System
Unifying Data at Memory Speed
BIG DATA ECOSYSTEM ISSUES
GlusterFS InterfaceAmazon S3 Interface Swift InterfaceHDFS Interface
4
BIG DATA ECOSYSTEM YESTERDAY

5. 5

6. 6

7. 7
• Fastest growing open-
source project in the
big data ecosystem
• 450+ contributors from
100+ organizations
• Running in large
production clusters
• Community members
are welcome!
FASTEST GROWING BIG DATA PROJECTS
Popular Open Source Projects’ Growth
Months
NumberofContributors

8. 8
Unification
New workflows across any
data in any storage system
Orders of magnitude
improvement in run time
Choice in compute and
storage – grow each
independently, buy only
what is needed
Performance Flexibility
ALLUXIO BENEFITS

9. #1 – ACCELERATING REMOTE STORAGE I/O
9
• Scenario: Compute and Storage Separation
• Meet different compute and storage hardware requirements
• Scale compute and storage independently
• Store data in traditional filers/SANs and object stores
• Analyze existing data with Big Data compute frameworks
• Limitation
• Accessing data requires remote I/O

10. I/O WITHOUT ALLUXIO
Spark
Storage
Low latency, memory
throughput
High latency, network
throughput
10

11. I/O WITH ALLUXIO
Spark
Storage
Alluxio
Keeping data in Alluxio
accelerates data access
11

12. CASE STUDY: BAIDU
12
The performance was amazing. With Spark
SQL alone, it took 100-150 seconds to finish a
query; using Alluxio, where data may hit local
or remote Alluxio nodes, it took 10-15 seconds.
- Baidu
RESULTS
• Data queries are now 30x faster with Alluxio
• Alluxio cluster runs stably, providing over
50TB of RAM space
• By using Alluxio, batch queries usually lasting
over 15 minutes were transformed into an
interactive query taking less than 30 seconds
Baidu’s PMs and analysts run
interactive queries to gain insights
into their products and business
• 200+ nodes deployment
• 2+ petabytes of storage
• Mix of memory + HDD
ALLUXIO
Baidu File System

13. #2 – SHARING DATA AT MEMORY-SPEED AMONG
APPLICATIONS
• Scenario: Data Sharing Architecture
• Pipelines: output of one job is input of the next job
• Applications, jobs, and contexts reading the same data
• Limitation
• Sharing data requires I/O
13

14. SHARING WITHOUT ALLUXIO
Spark
Storage
MapReduce Spark
Network I/O
Disk I/O
I/O slows down
sharing
14

15. SHARING WITH ALLUXIO
Spark
Storage
MapReduce Spark
Memory-speed
sharing
Alluxio
15

16. CASE STUDY: BARCLAYS
Thanks to Alluxio, we now have the raw data
immediately available at every iteration and
we can skip the costs of loading in terms of
time waiting, network traffic, and RDBMS
activity.
- Barclays
RESULTS
• Barclays workflow iteration time decreased
from hours to seconds
• Alluxio enabled workflows that were
impossible before
• By keeping data only in memory, the I/O cost
of loading and storing in Alluxio is now on the
order of seconds
Barclays uses query and machine
learning to train models for risk
management
• 6 node deployment
• 1TB of storage
• Memory only
ALLUXIO
Relational Database
16

17. #3 – UNIFYING DATA ACCESS FROM DIFFERENT
STORAGE
• Scenario: Multiple Storage Systems
• Most enterprises have multiple storage systems
• New (better, faster, cheaper) storage systems arise
• Limitation
• Accessing data from different systems requires different APIs
17

18. ACCESSING DATA THROUGH ALLUXIO
Storage B
Alluxio
Spark MapReduce Flink
Storage A Storage C
Flexible,
simple
no application
changes,
new mount
point
18

19. CASE STUDY: QUNAR
We’ve been running Alluxio in production for
over 9 months, Alluxio’s unified namespace
enable different applications and
frameworks to easily interact with data from
different storage systems.
- Qunar
RESULTS
• Data sharing among Spark Streaming, Spark
batch and Flink jobs provide efficient data
sharing
• Improved the performance of their system
with 15x – 300x speedups
• Tiered storage feature manages storage
resources including memory and HDD
• 200+ nodes deployment
• 6 billion logs (4.5 TB) daily
• Mix of Memory + HDD
ALLUXIO
Qunar uses real-time machine
learning for their website ads.
19

20. ALLUXIO DEMO

21. SUMMARY
21
• Adopted by industry leaders
• Unified, memory-speed data access across
compute frameworks (Spark, Presto,
MapReduce) and storage systems (S3, GCS,
ECS, Ceph, HDFS, NFS, etc)
• Rapidly growing OS community

22. JOIN THE COMMUNITY
22
Contribute @ www.alluxio.org/contribute
Get started @ goo.gl/55ApFx

23. Contact: gene@alluxio.com
Twitter: @unityxx
Websites: www.alluxio.com and www.alluxio.org
Thank you!
We are hiring!
Demo Videos:
Spark + Alluxio + S3
Alluxio Unified Namespace
23