A key design decision for data systems is whether they follow the row-store or the column-store paradigm. The former supports transactional workloads, while the latter is better for analytical queries. This decision has a significant impact on the entire data system architecture. The multiple-decadelong journey of these two designs has led to a new family of hybrid transactional/analytical processing (HTAP) architectures. Several efforts have been proposed to reap the benefits of both worlds by proposing systems that maintain multiple copies of data (in different physical layouts) and convert them into the desired layout as required. Due to data duplication, the additional necessary bookkeeping, and the cost of converting data between different layouts, these systems compromise between efficient analytics and data freshness. We depart from existing designs by proposing a radically new approach.
We ask the question: “What if we could access any layout and ship only the relevant data through the memory hierarchy by transparently converting rows to (arbitrary groups of) columns?” To achieve this functionality, we capitalize on the reinvigorated trend of hardware specialization (that has been accelerated due to the tapering of Moore's law) to propose Relational Fabric, a near-data vertical partitioner that allows memory or storage components to perform on-the-fly transparent data transformation. By exposing an intuitive API, Relational Fabric pushes vertical partitioning to the hardware, which profoundly impacts the process of designing and building data systems. (A) There is no need for data duplication and layout conversion, making HTAP systems viable using a single layout. (B) It simplifies the memory and storage manager that needs to maintain and update a single data layout. (C) It reduces unnecessary data movement through the memory hierarchy, allowing for better hardware utilization and, ultimately, better performance. In this paper, we present Relational Fabric for both memory and storage. We present our initial results on Relational Fabric for in-memory systems and discuss the challenges of building this hardware and the opportunities it brings for simplicity and innovation in the data system software stack, including physical design, query optimization, query evaluation, and concurrency control.
more »
« less
Relational Fabric: Transparent Data Transformation
A key design decision for data systems is whether they follow the row-store or the column-store paradigm. The former supports transactional workloads, while the latter is better for analytical queries. This decision has a profound impact on the entire data system architecture. The multiple-decadelong journey of these two designs has led to a new family of hybrid transactional/analytical processing (HTAP) architectures. Several efforts have been proposed to reap the benefits of both worlds by proposing systems that maintain multiple copies of data (in different physical layouts) and convert them into the desired layout as required. Due to data duplication, the additional necessary bookkeeping, and the cost of converting data between different layouts, these systems compromise between efficient analytics and data freshness. We depart from existing designs by proposing a radically new approach. We ask the question: “What if we could access any layout and ship only the relevant data through the memory hierarchy by transparently converting rows to (arbitrary groups of) columns?”
To achieve this functionality, we capitalize on the reinvigorated trend of hardware specialization (that has been accelerated due to the tapering of Moore’s law) to propose Relational Fabric, a near-data vertical partitioner that allows memory or storage component to perform on-the-fly transparent data transformation. By exposing an intuitive API, Relational Fabric pushes vertical partitioning to the hardware, which has a profound impact on the process of designing and building data systems. (A) There is no need for data duplication and layout conversion, making HTAP systems viable using a single layout. (B) It simplifies the memory and storage manager that needs to maintain and update a single data layout. (C) It reduces unnecessary data movement through the memory hierarchy allowing for better hardware utilization, and ultimately better performance. In this paper, we present Relational Fabric for both memory and storage. We present our initial results on Relational Fabric for in-memory systems and discuss the challenges of building this hardware, as well as the opportunities it brings for simplicity and innovation in the data system software stack, including physical design, query optimization, query evaluation, and concurrency control.
more »
« less
- Award ID(s):
- 2008799
- NSF-PAR ID:
- 10482045
- Publisher / Repository:
- IEEE
- Date Published:
- Journal Name:
- IEEE 39th International Conference on Data Engineering (ICDE'23)
- Page Range / eLocation ID:
- 3688 to 3698
- Format(s):
- Medium: X
- Location:
- Anaheim, CA, USA
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Hybrid Transactional and Analytical Processing (HTAP) systems suffer from workload interference at the software and hardware level. We examine workload interference for HTAP systems and highlight investigation directions to mitigate the interference. We use the popular two-copy HTAP architecture. The OLTP and OLAP sides are independent components with their own private copies of the data. The OLTP side is a row-store, whereas the OLAP side is a column-store. The OLTP and OLAP sides are connected by means of an intermediate data structure, delta, that keeps track of the fresh tuples that are generated by the OLTP side, but not yet transferred to the OLAP side. OLTP transactions register their modifications to delta before committing. OLAP queries first prop- agate fresh tuples from the OLTP side to the OLAP side and then perform query execution over the data at the OLAP side. HTAP systems suffer from interference at both the software and hardware level. Software-level interference depends on the OLTP and fresh tuple propagation throughput. In order to minimize interference, HTAP systems should ensure that fresh tuple propagation throughput is greater than the throughput of the OLTP transactions that generate the fresh tuples. Hardware-level interference depends on the demand for shared resources such as LLC and memory bandwidth by the OLTP and OLAP workloads. HTAP systems should isolate the OLTP and OLAP workloads in the shared resources and use micro-architectural re- source allocation policies that assign the optimal amount of re- sources to OLTP and OLAP workloads to minimize hardware-level interference.more » « less
-
Data-intensive analytical applications need to support both efficient reads and writes. However, what is usually a good data layout for an update-heavy workload, is not well-suited for a read-mostly one and vice versa. Modern analytical data systems rely on columnar layouts and employ delta stores to inject new data and updates. We show that for hybrid workloads we can achieve close to one order of magnitude better performance by tailoring the column layout design to the data and query workload. Our approach navigates the possible design space of the physical layout: it organizes each column’s data by determining the number of partitions, their corresponding sizes and ranges, and the amount of buffer space and how it is allocated. We frame these design decisions as an optimization problem that, given workload knowledge and performance requirements, provides an optimal physical layout for the workload at hand. To evaluate this work, we build an in-memory storage engine, Casper, and we show that it outperforms state-of-the-art data layouts of analytical systems for hybrid workloads. Casper delivers up to 2.32x higher throughput for update-intensive workloads and up to 2.14x higher throughput for hybrid workloads. We further show how to make data layout decisions robust to workload variation by carefully selecting the input of the optimization.more » « less
-
As large scale data processing becomes an ever more prominent component of modern computing tasks, databases now exist as a fundamental necessity of most computational platforms. However, in many cases there exists a disparity between the specializations of database management systems and the needs of the applications that run on them. The distinction between transactional and analyt- ical workloads for databases has been well established, but not fully addressed within the space of the most widely used embedded data- base system, namely SQLite3. To overcome this shortcoming, we implement SQLite3/HE, an analytical database engine implemented as an alternative execution path for SQLite. Through the utilization of an additional, complementary storage layer, SQLite3/HE trans- forms SQLite into a hybrid database system, able to fully leverage the benefits of both row and columnar storage layouts. SQLite3/HE improves the performance of analytical queries in the 100x-1000x speedup range, at no cost to the existing transactional query perfor- mance. These results validate the decision to implement SQLite3/HE as an alternative execution path, enabling it to serve as a drop-in replacement for SQLite3 in existing systems.more » « less
-
Serving deep learning models from relational databases brings significant benefits. First, features extracted from databases do not need to be transferred to any decoupled deep learning systems for inferences, and thus the system management overhead can be significantly reduced. Second, in a relational database, data management along the storage hierarchy is fully integrated with query processing, and thus it can continue model serving even if the working set size exceeds the available memory. Applying model deduplication can greatly reduce the storage space, memory footprint, cache misses, and inference latency. However, existing data deduplication techniques are not applicable to the deep learning model serving applications in relational databases. They do not consider the impacts on model inference accuracy as well as the inconsistency between tensor blocks and database pages. This work proposed synergistic storage optimization techniques for duplication detection, page packing, and caching, to enhance database systems for model serving. Evaluation results show that our proposed techniques significantly improved the storage efficiency and the model inference latency, and outperformed existing deep learning frameworks in targeting scenarios.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/ICDE55515.2023.00297
