Refine
Document Type
- Conference proceeding (38)
- Journal article (5)
- Book chapter (5)
Has full text
- yes (48)
Is part of the Bibliography
- yes (48)
Institute
- Informatik (48)
Publisher
Database management systems (DBMS) are critical performance components in large scale applications under modern update intensive workloads. Additional access paths accelerate look-up performance in DBMS for frequently queried attributes, but the required maintenance slows down update performance. The ubiquitous B+ tree is a commonly used key-indexed access path that is able to support many required functionalities with logarithmic access time to requested records. Modern processing and storage technologies and their characteristics require reconsideration of matured indexing approaches for today's workloads. Partitioned B-trees (PBT) leverage characteristics of modern hardware technologies and complex memory hierarchies as well as high update rates and changes in workloads by maintaining partitions within one single B+-Tree. This paper includes an experimental evaluation of PBTs optimized write pattern and performance improvements. With PBT transactional throughput under TPC-C increases 30%; PBT results in beneficial sequential write patterns even in presence of updates and maintenance operations.
The tale of 1000 cores: an evaluation of concurrency control on real(ly) large multi-socket hardware
(2020)
In this paper, we set out the goal to revisit the results of “Starring into the Abyss [...] of Concurrency Control with [1000] Cores” and analyse in-memory DBMSs on today’s large hardware. Despite the original assumption of the authors, today we do not see single-socket CPUs with 1000 cores. Instead multi-socket hardware made its way into production data centres. Hence, we follow up on this prior work with an evaluation of the characteristics of concurrency control schemes on real production multi-socket hardware with 1568 cores. To our surprise, we made several interesting findings which we report on in this paper.
In our initial DaMoN paper, we set out the goal to revisit the results of “Starring into the Abyss [...] of Concurrency Control with [1000] Cores” (Yu in Proc. VLDB Endow 8: 209-220, 2014). Against their assumption, today we do not see single-socket CPUs with 1000 cores. Instead, multi-socket hardware is prevalent today and in fact offers over 1000 cores. Hence, we evaluated concurrency control (CC) schemes on a real (Intel-based) multi-socket platform. To our surprise, we made interesting findings opposing results of the original analysis that we discussed in our initial DaMoN paper. In this paper, we further broaden our analysis, detailing the effect of hardware and workload characteristics via additional real hardware platforms (IBM Power8 and 9) and the full TPC-C transaction mix. Among others, we identified clear connections between the performance of the CC schemes and hardware characteristics, especially concerning NUMA and CPU cache. Overall, we conclude that no CC scheme can efficiently make use of large multi-socket hardware in a robust manner and suggest several directions on how CC schemes and overall OLTP DBMS should evolve in future.
Database management systems and K/V-Stores operate on updatable datasets – massively exceeding the size of available main memory. Tree-based K/V storage management structures became particularly popular in storage engines. B+ -Trees [1, 4] allow constant search performance, however write-heavy workloads yield in inefficient write patterns to secondary storage devices and poor performance characteristics. LSM-Trees [16, 23] overcome this issue by horizontal partitioning fractions of data – small enough to fully reside in main memory, but require frequent maintenance to sustain search performance.
Firstly, we propose Multi-Version Partitioned BTrees (MV-PBT) as sole storage and index management structure in key-sorted storage engines like K/V-Stores. Secondly, we compare MV-PBT against LSM-Trees. The logical horizontal partitioning in MV-PBT allows leveraging recent advances in modern B+ -Tree techniques in a small transparent and memory resident portion of the structure. Structural properties sustain steady read performance, yielding efficient write patterns and reducing write amplification.
We integrated MV-PBT in the WiredTiger [15] KV storage engine. MV-PBT offers an up to 2× increased steady throughput in comparison to LSM-Trees and several orders of magnitude in comparison to B+ -Trees in a YCSB [5] workload.
Asymmetric read/write storage technologies such as Flash are becoming
a dominant trend in modern database systems. They introduce
hardware characteristics and properties which are fundamentally
different from those of traditional storage technologies such
as HDDs.
Multi-Versioning Database Management Systems (MV-DBMSs)
and Log-based Storage Managers (LbSMs) are concepts that can
effectively address the properties of these storage technologies but
are designed for the characteristics of legacy hardware. A critical
component of MV-DBMSs is the invalidation model: commonly,
transactional timestamps are assigned to the old and the new version,
resulting in two independent (physical) update operations.
Those entail multiple random writes as well as in-place updates,
sub-optimal for new storage technologies both in terms of performance
and endurance. Traditional page-append LbSM approaches
alleviate random writes and immediate in-place updates, hence reducing
the negative impact of Flash read/write asymmetry. Nevertheless,
they entail significant mapping overhead, leading to write
amplification.
In this work we present an approach called Snapshot Isolation
Append Storage Chains (SIAS-Chains) that employs a combination
of multi-versioning, append storage management in tuple granularity
and novel singly-linked (chain-like) version organization.
SIAS-Chains features: simplified buffer management, multi-version
indexing and introduces read/write optimizations to data placement
on modern storage media. SIAS-Chains algorithmically avoids
small in-place updates, caused by in-place invalidation and converts
them into appends. Every modification operation is executed
as an append and recently inserted tuple versions are co-located.
In the present paper we demonstrate the novel technique to apply the recently proposed approach of In-Place Appends – overwrites on Flash without a prior erase operation. IPA can be applied selectively: only to DB-objects that have frequent and relatively small updates. To do so we couple IPA to the concept of NoFTL regions, allowing the DBA to place update-intensive DB-objects into special IPA-enabled regions. The decision about region configuration can be (semi-)automated by an advisor analyzing DB-log files in the background.
We showcase a Shore-MT based prototype of the above approach, operating on real Flash hardware. During the demonstration we allow the users to interact with the system and gain hands-on experience under different demonstration scenarios.
When forecasting sales figures, not only the sales history but also the future price of a product will influence the sales quantity. At first sight, multivariate time series seem to be the appropriate model for this task. Nontheless, in real life history is not always repeatable, i.e. in the case of sales history there is only one price for a product at a given time. This complicates the design of a multivariate time series. However, for some seasonal or perishable products the price is rather a function of the expiration date than of the sales history. This additional information can help to design a more accurate and causal time series model. The proposed solution uses an univariate time series model but takes the price of a product as a parameter that influences systematically the prediction. The price influence is computed based on historical sales data using correlation analysis and adjustable price ranges to identify products with comparable history. Compared to other techniques this novel approach is easy to compute and allows to preset the price parameter for predictions and simulations. Tests with data from the Data Mining Cup 2012 demonstrate better results than established sophisticated time series methods.
In this paper, we present a new approach for achieving robust performance of data structures making it easier to reuse the same design for different hardware generations but also for different workloads. To achieve robust performance, the main idea is to strictly separate the data structure design from the actual strategies to execute access operations and adjust the actual execution strategies by means of so-called configurations instead of hard-wiring the execution strategy into the data structure. In our evaluation we demonstrate the benefits of this configuration approach for individual data structures as well as complex OLTP workloads.
In this paper we present our work in progress on revisiting traditional DBMS mechanisms to manage space on native Flash and how it is administered by the DBA. Our observations and initial results show that: the standard logical database structures can be used for physical organization of data on native Flash; at the same time higher DBMS performance is achieved without incurring extra DBA overhead. Initial experimental evaluation indicates a 20% increase in transactional throughput under TPC-C, by performing intelligent data placement on Flash, less erase operations and thus better Flash longevity.
Current data-intensive systems suffer from scalability as they transfer massive amounts of data to the host DBMS to process it there. Novel near-data processing (NDP) DBMS architectures and smart storage can provably reduce the impact of raw data movement. However, transferring the result-set of an NDP operation may increase the data movement, and thus, the performance overhead. In this paper, we introduce a set of in-situ NDP result-set management techniques, such as spilling, materialization, and reuse. Our evaluation indicates a performance improvement of 1.13 × to 400 ×.
Real Time Charging (RTC) applications that reside in the telecommunications domain have the need for extremely fast database transactions. Today´s providers rely mostly on in-memory databases for this kind of information processing. A flexible and modular benchmark suite specifically designed for this domain provides a valuable framework to test the performance of different DB candidates. Besides a data and a load generator, the suite also includes decoupled database connectors and use case components for convenient customization and extension. Such easily produced test results can be used as guidance for choosing a subset of candidates for further tuning/testing and finally evaluating the database most suited to the chosen use cases. This is why our benchmark suite can be of value for choosing databases for RTC use cases.
The performance and scalability of modern data-intensive systems are limited by massive data movement of growing datasets across the whole memory hierarchy to the CPUs. Such traditional processor-centric DBMS architectures are bandwidth- and latency-bound. Processing-in-Memory (PIM) designs seek to overcome these limitations by integrating memory and processing functionality on the same chip. PIM targets near- or in-memory data processing, leveraging the greater in-situ parallelism and bandwidth.
In this paper, we introduce pimDB and provide an initial comparison of processor-centric and PIM-DBMS approaches under different aspects, such as scalability and parallelism, cache-awareness, or PIM-specific compute/bandwidth tradeoffs. The evaluation is performed end-to-end on a real PIM hardware system from UPMEM.
Massive data transfers in modern data intensive systems resulting from low data-locality and data-to-code system design hurt their performance and scalability. Near-data processing (NDP) and a shift to code-to-data designs may represent a viable solution as packaging combinations of storage and compute elements on the same device has become viable.
The shift towards NDP system architectures calls for revision of established principles. Abstractions such as data formats and layouts typically spread multiple layers in traditional DBMS, the way they are processed is encapsulated within these layers of abstraction. The NDP-style processing requires an explicit definition of cross-layer data formats and accessors to ensure in-situ executions optimally utilizing the properties of the underlying NDP storage and compute elements. In this paper, we make the case for such data format definitions and investigate the performance benefits under NoFTL-KV and the COSMOS hardware platform.
Massive data transfers in modern data-intensive systems resulting from low data-locality and data-to-code system design hurt their performance and scalability. Near-Data processing (NDP) and a shift to code-to-data designs may represent a viable solution as packaging combinations of storage and compute elements on the same device has become feasible. The shift towards NDP system architectures calls for revision of established principles. Abstractions such as data formats and layouts typically spread multiple layers in traditional DBMS, the way they are processed is encapsulated within these layers of abstraction. The NDP-style processing requires an explicit definition of cross-layer data formats and accessors to ensure in-situ executions optimally utilizing the properties of the underlying NDP storage and compute elements. In this paper, we make the case for such data format definitions and investigate the performance benefits under RocksDB and the COSMOS hardware platform.
Near-Data Processing (NDP) is a key computing paradigm for reducing the ever growing time and energy costs of data transport versus computations. With their flexibility, FPGAs are an especially suitable compute element for NDP scenarios. Even more promising is the exploitation of novel and future non-volatile memory (NVM) technologies for NDP, which aim to achieve DRAM-like latencies and throughputs, while providing large capacity non-volatile storage.
Experimentation in using FPGAs in such NVM-NDP scenarios has been hindered, though, by the fact that the NVM devices/FPGA boards are still very rare and/or expensive. It thus becomes useful to emulate the access characteristics of current and future NVMs using off-the-shelf DRAMs. If such emulation is sufficiently accurate, the resulting FPGA-based NDP computing elements can be used for actual full-stack hardware/software benchmarking, e.g., when employed to accelerate a database.
For this use, we present NVMulator, an open-source easy-to-use hardware emulation module that can be seamlessly inserted between the NDP processing elements on the FPGA and a conventional DRAM-based memory system. We demonstrate that, with suitable parametrization, the emulated NVM can come very close to the performance characteristics of actual NVM technologies, specifically Intel Optane. We achieve 0.62% and 1.7% accuracy for cache line sized accesses for read and write operations, while utilizing only 0.54% of LUT logic resources on a Xilinx/AMD AU280 UltraScale+ FPGA board. We consider both file-system as well as database access patterns, examining the operation of the RocksDB database when running on real or emulated Optane-technology memories.
Modern persistent Key/Value stores are designed to meet the demand for high transactional throughput and high data ingestion rates. Still, they rely on backwards-compatible storage stack and abstractions to ease space management, foster seamless proliferation and system integration. Their dependence on the traditional I/O stack has negative impact on performance, causes unacceptably high write-amplification, and limits the storage longevity.
In the present paper we present NoFTL KV, an approach that results in a lean I/O stack, integrating physical storage management natively in the Key/Value store. NoFTL-KV eliminates backwards compatibility, allowing the Key/Value store to directly consume the characteristics of modern storage technologies. NoFTLKV is implemented under RocksDB. The performance evaluation under LinkBench shows that NoFTL-KV improves transactional throughput by 33%, while response times improve up to 2.3x. Furthermore, NoFTL KV reduces write-amplification 19x and improves storage longevity by imately the same factor.
Flash SSDs are omnipresent as database storage. HDD replacement is seamless since Flash SSDs implement the same legacy hardware and software interfaces to enable backward compatibility. Yet, the price paid is high as backward compatibility masks the native behaviour, incurs significant complexity and decreases I/O performance, making it non-robust and unpredictable. Flash SSDs are black-boxes. Although DBMS have ample mechanisms to control hardware directly and utilize the performance potential of Flash memory, the legacy interfaces and black-box architecture of Flash devices prevent them from doing so.
In this paper we demonstrate NoFTL, an approach that enables native Flash access and integrates parts of the Flashmanagement functionality into the DBMS yielding significant performance increase and simplification of the I/O stack. NoFTL is implemented on real hardware based on the OpenSSD research platform. The contributions of this paper include: (i) a description of the NoFTL native Flash storage architecture; (ii) its integration in Shore-MT and (iii) performance evaluation of NoFTL on a real Flash SSD and on an on-line data-driven Flash emulator under TPCB, C,E and H workloads. The performance evaluation results indicate an improvement of at least 2.4x on real hardware over conventional Flash storage; as well as better utilisation of native Flash parallelism.
Massive data transfers in modern key/value stores resulting from low data-locality and data-to-code system design hurt their performance and scalability. Near-data processing (NDP) designs represent a feasible solution, which although not new, have yet to see widespread use.
In this paper we introduce nKV, which is a key/value store utilizing native computational storage and near-data processing. On the one hand, nKV can directly control the data and computation placement on the underlying storage hardware. On the other hand, nKV propagates the data formats and layouts to the storage device where, software and hardware parsers and accessors are implemented. Both allow NDP operations to execute in host-intervention-free manner, directly on physical addresses and thus better utilize the underlying hardware. Our performance evaluation is based on executing traditional KV operations (GET, SCAN) and on complex graph-processing algorithms (Betweenness Centrality) in-situ, with 1.4×-2.7× better performance on real hardware – the COSMOS+ platform.
nKV in action: accelerating KVstores on native computational storage with NearData processing
(2020)
Massive data transfers in modern data intensive systems resulting from low data-locality and data-to-code system design hurt their performance and scalability. Near-data processing (NDP) designs represent a feasible solution, which although not new, has yet to see widespread use.
In this paper we demonstrate various NDP alternatives in nKV, which is a key/value store utilizing native computational storage and near-data processing. We showcase the execution of classical operations (GET, SCAN) and complex graph-processing algorithms (Betweenness Centrality) in-situ, with 1.4x-2.7x better performance due to NDP. nKV runs on real hardware - the COSMOS+ platform.
Multi-versioning and MVCC are the foundations of many modern DBMSs. Under mixed workloads and large datasets, the creation of the transactional snapshot can become very expensive, as long-running analytical transactions may request old versions, residing on cold storage, for reasons of transactional consistency. Furthermore, analytical queries operate on cold data, stored on slow persistent storage. Due to the poor data locality, snapshot creation may cause massive data transfers and thus lower performance. Given the current trend towards computational storage and near-data processing, it has become viable to perform such operations in-storage to reduce data transfers and improve scalability. neoDBMS is a DBMS designed for near-data processing and computational storage. In this paper, we demonstrate how neoDBMS performs snapshot computation in-situ. We showcase different interactive scenarios, where neoDBMS outperforms PostgreSQL 12 by up to 5×.