An official website of the United States government
We present Vizier, a multi-modal data exploration and debugging tool. The system supports a wide range of operations by seamlessly integrating Python, SQL, and automated data curation and debugging methods. Using Spark as an execution backend, Vizier handles large datasets in multiple formats. Ease-of-use is attained through integration of a notebook with a spreadsheet-style interface and with visualizations that guide and support the user in the loop. In addition, native support for provenance and versioning enable collaboration and uncertainty management. In this demonstration we will illustrate the diverse features of the system using several realistic data science tasks based on real data.
more »
« less
A High-Performance Distributed Relational Database System for Scalable OLAP Processing
We present HRDBMS, a novel distributed shared-nothing database system developed with the goal of improving scalability of MPP databases based on a principled combination of techniques from MPP and Big Data systems with novel communication and work-distribution techniques. HRDBMS runs on a custom distributed and asynchronous execution engine that features highly parallelized operator implementations. The system features a cost-based optimization framework, user-defined data partitioning, locality-aware query execution, a non-blocking and hierarchical shuffle, and data skipping based on caching predicate matches. Our experimental comparison with Hive, Spark SQL, and Greenplum confirms that HRDBMS’s scalability is on par with Hive and Spark SQL (up to 96 nodes) while its per-node performance can compete with MPP databases (Greenplum).
more »
« less
- Award ID(s):
- 1640864
- PAR ID:
- 10129192
- Date Published:
- Journal Name:
- IPDPS
- Page Range / eLocation ID:
- 738 to 748
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The goal of this thesis is to introduce a new design for building federated query optimizers, based on machine learning. We propose a modular and flexible architecture, allowing a federated query optimizer to integrate with any database system that supports SQL, with close-to-zero engineering effort. By observing the performance of the external systems, our optimizer learns and builds cost models on-the-fly, enabling federated query optimization with negligible communication with the external systems. To demonstrate the potential of this research plan, we present a prototype of our federated query optimizer built on top of Spark SQL. Our implementation effectively accelerates federated queries, achieving up to 7.5x better query execution times compared to the vanilla implementation of Spark SQL.more » « less
-
Resource disaggregation (RD) is an emerging paradigm for data center computing whereby resource-optimized servers are employed to minimize resource fragmentation and improve resource utilization. Apache Spark deployed under the RD paradigm employs a cluster of compute-optimized servers to run executors and a cluster of storage-optimized servers to host the data on HDFS. However, the network transfer from storage to compute cluster becomes a severe bottleneck for big data processing. Near-data processing (NDP) is a concept that aims to alleviate network load in such cases by offloading (or “pushing down”) some of the compute tasks to the storage cluster. Employing NDP for Spark under the RD paradigm is challenging because storage-optimized servers have limited computational resources and cannot host the entire Spark processing stack. Further, even if such a lightweight stack could be developed and deployed on the storage cluster, it is not entirely obvious which Spark queries would benefit from pushdown, and which tasks of a given query should be pushed down to storage. This paper presents the design and implementation of a near-data processing system for Spark, SparkNDP, that aims to address the aforementioned challenges. SparkNDP works by implementing novel NDP Spark capabilities on the storage cluster using a lightweight library of SQL operators and then developing an analytical model to help determine which Spark tasks should be pushed down to storage based on the current network and system state. Simulation and prototype implementation results show that SparkNDP can help reduce Spark query execution times when compared to both the default approach of not pushing down any tasks to storage and the outright NDP approach of pushing all tasks to storage.more » « less
-
The performance of modern Big Data frameworks, e.g. Spark, depends greatly on high-speed storage and shuffling, which impose a significant memory burden on production data centers. In many production situations, the persistence and shuffling intensive applications can suffer a major performance loss due to lack of memory. Thus, the common practice is usually to over-allocate the memory assigned to the data workers for production applications, which in turn reduces overall resource utilization. One efficient way to address the dilemma between the performance and cost efficiency of Big Data applications is through data center computing resource disaggregation. This paper proposes and implements a system that incorporates the Spark Big Data framework with a novel in-memory distributed file system to achieve memory disaggregation for data persistence and shuffling. We address the challenge of optimizing performance at affordable cost by co-designing the proposed in-memory distributed file system with large-volume DIMM-based persistent memory (PMEM) and RDMA technology. The disaggregation design allows each part of the system to be scaled independently, which is particularly suitable for cloud deployments. The proposed system is evaluated in a production-level cluster using real enterprise-level Spark production applications. The results of an empirical evaluation show that the system can achieve up to a 3.5- fold performance improvement for shuffle-intensive applications with the same amount of memory, compared to the default Spark setup. Moreover, by leveraging PMEM, we demonstrate that our system can effectively increase the memory capacity of the computing cluster with affordable cost, with a reasonable execution time overhead with respect to using local DRAM only.more » « less
-
Due to its speed and ease of use, Spark has become a popular tool amongst data scientists to analyze data in various sizes. Counter-intuitively, data processing workloads in industrial companies such as Google, Facebook, and Yahoo are dominated by short-running applications, which is due to the majority of applications being mostly consisted of simple SQL-like queries (Dean, 2004, Zaharia et al, 2008). Unfortunately, the current version of Spark is not optimized for such kinds of workloads. In this paper, we propose a novel framework, called Meteor, which can dramatically improve the performance for short-running applications. We extend Spark with three additional operating modes: one-thread, one-container, and distributed. The one-thread mode executes all tasks on just one thread; the one-container mode runs these tasks in one container by multi-threading; the distributed mode allocates all tasks over the whole cluster. A new framework for submitting applications is also designed, which utilizes a fine-grained Spark performance model to decide which of the three modes is the most efficient to invoke upon a new application submission. From our extensive experiments on Amazon EC2, one-thread mode is the optimal choice when the input size is small, otherwise the distributed mode is better. Overall, Meteor is up to 2 times faster than the original Spark for short applications.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/IPDPS.2019.00083
