Reshape: Adaptive Result-aware Skew Handling for Exploratory Analysis on Big Data

TL;DR

Reshape is a framework that adaptively mitigates partitioning skew during data analysis workflows, improving initial result representativeness and efficiency in big data systems.

Contribution

It introduces a novel, adaptive, two-phase skew handling framework that adjusts load distribution during execution, reducing user burden and supporting multiple operators.

Findings

Reshape effectively reduces skew during execution.

It improves the representativeness of initial results.

Demonstrates efficiency on Amber and Flink systems.

Abstract

The process of data analysis, especially in GUI-based analytics systems, is highly exploratory. The user iteratively refines a workflow multiple times before arriving at the final workflow. In such an exploratory setting, it is valuable to the user if the initial results of the workflow are representative of the final answers so that the user can refine the workflow without waiting for the completion of its execution. Partitioning skew may lead to the production of misleading initial results during the execution. In this paper, we explore skew and its mitigation strategies from the perspective of the results shown to the user. We present a novel framework called Reshape that can adaptively handle partitioning skew in pipelined execution. Reshape employs a two-phase approach that transfers load in a fine-tuned manner to mitigate skew iteratively during execution, thus enabling it to handle changes in input-data distribution. Reshape has the ability to adaptively adjust skew-handling parameters, which reduces the technical burden on the users. Reshape supports a variety of operators such as HashJoin, Group-by, and Sort. We implemented Reshape on top of two big data engines, namely Amber and Flink, to demonstrate its generality and efficiency, and report an experimental evaluation using real and synthetic datasets.