hive-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Dmitriy V. Ryaboy (JIRA)" <>
Subject [jira] [Commented] (HIVE-4160) Vectorized Query Execution in Hive
Date Wed, 03 Jul 2013 23:16:20 GMT


Dmitriy V. Ryaboy commented on HIVE-4160:

Hi folks,
What an incredible amount of work! Looks fantastic, looking forward to this.

It seems like the general idea of a vectorized operator is not Hive-specific. Is there any
possibility of abstracting the core logic of an operator that can efficiently process a stream
of data, such as what you get from ORCFile, and return the computed results?

Having such a library be available independently of Hive would allow reuse in other Hadoop
ecosystem projects (Pig, Cascading, Drill, etc) without the need to reinvent the wheel, and
would also bring the whole community behind optimizing one set of operators instead of continuing
the existing fragmented state of the world. 

The process of separating out such a library might also yield benefits in terms of winding
up with a cleaner design and better abstractions (that's been my experience when going through
similar exercises on other projects -- I don't have any reason to think your current design
is not clean or doesn't have good abstractions).

Do you have any thoughts on how this could be achieved? Does this sound like something you
would be interested in? Is there something that people currently working on other projects
can do to help this become a reality?

> Vectorized Query Execution in Hive
> ----------------------------------
>                 Key: HIVE-4160
>                 URL:
>             Project: Hive
>          Issue Type: New Feature
>            Reporter: Jitendra Nath Pandey
>            Assignee: Jitendra Nath Pandey
>         Attachments: Hive-Vectorized-Query-Execution-Design.docx, Hive-Vectorized-Query-Execution-Design-rev2.docx,
Hive-Vectorized-Query-Execution-Design-rev3.docx, Hive-Vectorized-Query-Execution-Design-rev3.docx,
Hive-Vectorized-Query-Execution-Design-rev3.pdf, Hive-Vectorized-Query-Execution-Design-rev4.docx,
Hive-Vectorized-Query-Execution-Design-rev4.pdf, Hive-Vectorized-Query-Execution-Design-rev5.docx,
Hive-Vectorized-Query-Execution-Design-rev5.pdf, Hive-Vectorized-Query-Execution-Design-rev6.docx,
Hive-Vectorized-Query-Execution-Design-rev6.pdf, Hive-Vectorized-Query-Execution-Design-rev7.docx,
Hive-Vectorized-Query-Execution-Design-rev8.docx, Hive-Vectorized-Query-Execution-Design-rev8.pdf,
Hive-Vectorized-Query-Execution-Design-rev9.docx, Hive-Vectorized-Query-Execution-Design-rev9.pdf
> The Hive query execution engine currently processes one row at a time. A single row of
data goes through all the operators before the next row can be processed. This mode of processing
is very inefficient in terms of CPU usage. Research has demonstrated that this yields very
low instructions per cycle [MonetDB X100]. Also currently Hive heavily relies on lazy deserialization
and data columns go through a layer of object inspectors that identify column type, deserialize
data and determine appropriate expression routines in the inner loop. These layers of virtual
method calls further slow down the processing. 
> This work will add support for vectorized query execution to Hive, where, instead of
individual rows, batches of about a thousand rows at a time are processed. Each column in
the batch is represented as a vector of a primitive data type. The inner loop of execution
scans these vectors very fast, avoiding method calls, deserialization, unnecessary if-then-else,
etc. This substantially reduces CPU time used, and gives excellent instructions per cycle
(i.e. improved processor pipeline utilization). See the attached design specification for
more details.

This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see:

View raw message