[HIVE-24503] Optimize vector row serde by avoiding type check at run time

• Type: Bug
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Component/s: Hive
• Labels: pull-request-available
• Assignee: mahesh kumar behera
• Reporter: mahesh kumar behera
• Created: 08/Dec/20 11:32
• Updated: 01/Feb/21 10:17
• Resolved: 01/Feb/21 10:17

Description

Serialization/Deserialization of vectorized batch done at VectorSerializeRow and VectorDeserializeRow does a type checking for each column of each row. This becomes very costly when there are billions of rows to read/write. This can be optimized if the type check is done during init time and specific reader/writer classes are created. This classes can be used directly stored in filed structure to avoid run time type check.

Issue Links

• relates to: HIVE-24443 Optimise VectorSerializeRow for primitives
• links to: GitHub Pull Request #1753