Spark User Survey
Name
This is a required question
Organization
This is a required question
Which components of the Spark stack are you using?
Never heard of it
Trying it out
Production
Spark
Shark (Hive on Spark)
Spark Streaming
Bagel
BlinkDB
Please enter one response per row
Where do you run Spark?
Private cluster - standalone mode
Private cluster - Mesos
Private cluster - YARN
Amazon EC2 - Spark scripts
Amazon Elastic MapReduce
Other:
This is a required question
How many nodes do you typically use?
1
2-5
6-20
21-100
101+
This is a required question
Which languages do you use Spark in?
Scala
Java
Python
This is a required question
Which environment do you use for development?
Linux / UNIX
Windows
Mac OS X
This is a required question
Which Spark version are you using?
0.5
0.6
0.7
0.8 (master branch)
This is a required question
What kinds of applications do you (hope to) use Spark for?
Already using
Currently prototyping
Want to investigate later
SQL queries
General data processing (in lieu of MapReduce, Pig, etc)
Machine learning
Graph computations
Stream processing
User-facing services (e.g. to serve queries for a web UI)
Please enter one response per row
Which resources did you use to learn Spark?
Official documentation (
http://spark.incubator.apache.org/docs/latest/
)
Video screencasts (
http://spark.incubator.apache.org/documentation.html
)
AMP Camp talks and online exercises
External blog posts / tutorials
Mailing lists
Other:
This is a required question
Which features of Spark do you consider most important for your use case(s)?
Ease of programming
Performance
Ease of deployment
Hive compatibility
Interactive shell
Other:
This is a required question
What aspects of the project do you think are most important to focus on next?
Continuous operation (master failover, metrics, etc)
Debugging tools
Documentation
Integration with other tools (list below)
Performance optimizations
Resource sharing
Standard libraries (e.g. machine learning, graph algorithms)
Other:
This is a required question
We're looking to make Spark easier to use with existing machine learning tools; which such tools do you currently use?
R
Python
Matlab
SAS
Other:
This is a required question
Please specify in more detail, or list other ideas to improve Spark. If you'd like us to contact you about an idea, include your email.
This is a required question
Any other feedback?
This is a required question
Add my organization to the Spark "Powered By" page
The community uses a wiki page (
https://cwiki.apache.org/confluence/display/SPARK/Powered+By+Spark
) to track organizations and projects using Spark. If you'd like us to add you, check below.
Add my organization's name to the list
This is a required question
Short description of organization/use-case for "Powered By" page
If you checked the above box to be added to the Powered By page, you can also provide a short text description of your organization/use-case to be included next to your name/link on the Powered By page.
This is a required question
Never submit passwords through Google Forms.