Log-Structured Merge-trees (LSM-trees) have been widely used in modern NoSQL systems. Due to their out-of-place update design, LSM-trees have introduced memory walls among the memory components of multiple LSM-trees and between the write memory and the buffer cache. Optimal memory allocation among these regions is non-trivial because it is highly workload-dependent. Existing LSM-tree implementations instead adopt static memory allocation schemes due to their simplicity and robustness, sacrificing performance. In this paper, we attempt to break down these memory walls in LSM-based storage systems. We first present a memory management architecture that enables adaptive memory management. We then present a partitioned memory component structure with new flush policies to better exploit the write memory to minimize the write cost. To break down the memory wall between the write memory and the buffer cache, we further introduce a memory tuner that tunes the memory allocation between these two regions. We have conducted extensive experiments in the context of Apache AsterixDB using the YCSB and TPC-C benchmarks and we present the results here.
In recent years, the Log Structured Merge (LSM) tree has been widely adopted by NoSQL and NewSQL systems for its superior write performance. Despite its popularity, however, most existing work has focused on LSM-based key-value stores with only a primary LSM-tree index; auxiliary structures, which are critical for supporting ad-hoc queries, have received much less attention. In this paper, we focus on efficient data ingestion and query processing for general-purpose LSM-based storage systems. We first propose and evaluate a series of optimizations for efficient batched point lookups, significa…
Recently, the Log-Structured Merge-tree (LSM-tree) has been widely adopted for use in the storage layer of modern NoSQL systems. Because of this, there have been a large number of research efforts, from both the database community and the operating systems community, that try to improve various aspects of LSM-trees. In this paper, we provide a survey of recent research efforts on LSM-trees so that readers can learn the state-of-the-art in LSM-based storage techniques. We provide a general taxonomy to classify the literature of LSM-trees, survey the efforts in detail, and discuss their strength…
This paper studies the design of B-tree that can take full advantage of modern storage hardware with built-in transparent compression. Recent years have witnessed significant interest in applying log-structured merge tree (LSM-tree) as an alternative to B-tree. The current consensus is that, compared with B-tree, LSM-tree has distinct advantages in terms of storage space efficiency and write amplification. This paper argues that one should revisit this belief upon the arrival of storage hardware with built-in transparent compression. Advanced storage appliances~(e.g., all-flash array) and emer…
The cloud infrastructure motivates disaggregation of monolithic data stores into components that are assembled together based on an application's workload. This study investigates disaggregation of an LSM-tree key-value store into components that communicate using RDMA. These components separate storage from processing, enabling processing components to share storage bandwidth and space. The processing components scatter blocks of a file (SSTable) across an arbitrary number of storage components and balance load across them using power-of-d. They construct ranges dynamically at runtime to para…
The Log-Structured Merge-Tree (LSM-tree) has been widely adopted for use in modern NoSQL systems for its superior write performance. Despite the popularity of LSM-trees, they have been criticized for suffering from write stalls and large performance variances due to the inherent mismatch between their fast in-memory writes and slow background I/O operations. In this paper, we use a simple yet effective two-phase experimental approach to evaluate write stalls for various LSM-tree designs. We further explore the design choices of LSM merge schedulers to minimize write stalls given an I/O bandwid…
In the last decade, key-value data storage systems have gained significantly more interest from academia and industry. These systems face numerous challenges concerning storage space- and read optimization. There exists a large potential for improving current solutions by introducing new management techniques and algorithms. In this paper we give an overview of the basic concept of key-value data storage systems and provide an explanation for bottlenecks. Further we introduce two new memory management algorithms and a improved index structure. Finally, these solutions are compared to each othe…
Document database systems store self-describing semi-structured records, such as JSON, "as-is" without requiring the users to pre-define a schema. This provides users with the flexibility to change the structure of incoming records without worrying about taking the system offline or hindering the performance of currently running queries. However, the flexibility of such systems does not free. The large amount of redundancy in the records can introduce an unnecessary storage overhead and impact query performance. Our focus in this paper is to address the storage overhead issue by introducing a …
Real-time analytics systems employ hybrid data layouts in which data are stored in different formats throughout their lifecycle. Recent data are stored in a row-oriented format to serve OLTP workloads and support high insert rates, while older data are transformed to a column-oriented format for OLAP access patterns. We observe that a Log-Structured Merge (LSM) Tree is a natural fit for a lifecycle-aware storage engine due to its high write throughput and level-oriented structure, in which records propagate from one level to the next over time. To build a lifecycle-aware storage engine using a…
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 allow constant search performance, however write-heavy workloads yield in inefficient write patterns to secondary storage devices and poor performance characteristics. LSM-Trees 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 p…
Persistent key-value (KV) stores mostly build on the Log-Structured Merge (LSM) tree for high write performance, yet the LSM-tree suffers from the inherently high I/O amplification. KV separation mitigates I/O amplification by storing only keys in the LSM-tree and values in separate storage. However, the current KV separation design remains inefficient under update-intensive workloads due to its high garbage collection (GC) overhead in value storage. We propose HashKV, which aims for high update performance atop KV separation under update-intensive workloads. HashKV uses hash-based data groupi…
Log-Structured Merge (LSM) Trees provide a tiered data storage and retrieval paradigm that is attractive for write-optimized data systems. Maintaining an efficient buffer in memory and deferring updates past their initial write-time, the structure provides quick operations over hot data. Because each layer of the structure is logically separate from the others, the structure is also conducive to opportunistic and granular optimization. In this paper, we introduce the Skiplist-Based LSM Tree (sLSM), a novel system in which the memory buffer of the LSM is composed of a sequence of skiplists. We …
The log-structured merge tree (LSM-tree) gains wide popularity in building key-value (KV) stores. It employs logs to back up arriving KV pairs and maintains a few on-disk levels with exponentially increasing capacity limits, resembling a tiered tree-like structure. A level comprises SST files, each of which holds a sequence of sorted KV pairs. From time to time, LSM-tree redeploys KV pairs from a full level to the lower level by compaction, which merge-sorts and moves KV pairs among SST files, thereby incurring substantial disk I/Os. In this paper, we revisit the design of LSM-tree and find th…
Log-Structured Merge trees (LSM trees) are increasingly used as the storage engines behind several data systems, frequently deployed in the cloud. Similar to other database architectures, LSM trees take into account information about the expected workload (e.g., reads vs. writes, point vs. range queries) to optimize their performance via tuning. Operating in shared infrastructure like the cloud, however, comes with a degree of workload uncertainty due to multi-tenancy and the fast-evolving nature of modern applications. Systems with static tuning discount the variability of such hybrid workloa…
Data-intensive applications fueled the evolution of log structured merge (LSM) based key-value engines that employ the out-of-place paradigm to support high ingestion rates with low read/write interference. These benefits, however, come at the cost of treating deletes as a second-class citizen. A delete inserts a tombstone that invalidates older instances of the deleted key. State-of-the-art LSM engines do not provide guarantees as to how fast a tombstone will propagate to persist the deletion. Further, LSM engines only support deletion on the sort key. To delete on another attribute (e.g., ti…
Log-structured merge (LSM) trees offer efficient ingestion by appending incoming data, and thus, are widely used as the storage layer of production NoSQL data stores. To enable competitive read performance, LSM-trees periodically re-organize data to form a tree with levels of exponentially increasing capacity, through iterative compactions. Compactions fundamentally influence the performance of an LSM-engine in terms of write amplification, write throughput, point and range lookup performance, space amplification, and delete performance. Hence, choosing the appropriate compaction strategy is c…
LSM-tree has been widely used in cloud computing systems by Google, Facebook, and Amazon, to achieve high performance for write-intensive workloads. However, in LSM-tree, random key-value queries can experience long latency and low throughput due to the interference from the compaction, a basic operation in the algorithm, to caching. LSM-tree relies on frequent compaction operations to merge data into a sorted structure. After a compaction, the original data are reorganized and written to other locations on the disk. As a result, the cached data are invalidated since their referencing addresse…
The design of the buffer manager in database management systems (DBMSs) is influenced by the performance characteristics of volatile memory (DRAM) and non-volatile storage (e.g., SSD). The key design assumptions have been that the data must be migrated to DRAM for the DBMS to operate on it and that storage is orders of magnitude slower than DRAM. But the arrival of new non-volatile memory (NVM) technologies that are nearly as fast as DRAM invalidates these previous assumptions. This paper presents techniques for managing and designing a multi-tier storage hierarchy comprising of DRAM, NVM, and…
We revisit column-oriented storage and query processing techniques in the context of contemporary graph database management systems (GDBMSs). Similar to column-oriented RDBMSs, GDBMSs support read-heavy analytical workloads that however have fundamentally different data access patterns than traditional analytical workloads. We first derive a set of desiderata for optimizing storage and query processors of GDBMS based on their access patterns. We then present the design of columnar storage, compression, and query processing techniques based on these desiderata. In addition to showing direct int…
Energy consumption has become a first-class optimization goal in design and implementation of data-intensive computing systems. This is particularly true in the design of database management systems (DBMS), which was found to be the major consumer of energy in the software stack of modern data centers. Among all database components, the storage system is one of the most power-hungry elements. In previous work, dynamic power management (DPM) techniques that make real-time decisions to transition the disks to low-power modes are normally used to save energy in storage systems. In this paper, we …
Spreadsheet software is the tool of choice for interactive ad-hoc data management, with adoption by billions of users. However, spreadsheets are not scalable, unlike database systems. On the other hand, database systems, while highly scalable, do not support interactivity as a first-class primitive. We are developing DataSpread, to holistically integrate spreadsheets as a front-end interface with databases as a back-end datastore, providing scalability to spreadsheets, and interactivity to databases, an integration we term presentational data management (PDM). In this paper, we make a first st…
Finding the best way to leverage non-volatile memory (NVM) on modern database systems is still an open problem. The answer is far from trivial since the clear boundary between memory and storage present in most systems seems to be incompatible with the intrinsic memory-storage duality of NVM. Rather than treating NVM either solely as memory or solely as storage, in this work we propose how NVM can be simultaneously used as both in the context of modern database systems. We design a persistent buffer pool on NVM, enabling pages to be directly read/written by the CPU (like memory) while recoveri…
Near-Data Processing refers to an architectural hardware and software paradigm, based on the co-location of storage and compute units. Ideally, it will allow to execute application-defined data- or compute-intensive operations in-situ, i.e. within (or close to) the physical data storage. Thus, Near-Data Processing seeks to minimize expensive data movement, improving performance, scalability, and resource-efficiency. Processing-in-Memory is a sub-class of Near-Data processing that targets data processing directly within memory (DRAM) chips. The effective use of Near-Data Processing mandates new…
Parallel shared-nothing data management systems have been widely used to exploit a cluster of machines for efficient and scalable data processing. When a cluster needs to be dynamically scaled in or out, data must be efficiently rebalanced. Ideally, data rebalancing should have a low data movement cost, incur a small overhead on data ingestion and query processing, and be performed online without blocking reads or writes. However, existing parallel data management systems often exhibit certain limitations and drawbacks in terms of efficient data rebalancing. In this paper, we introduce DynaHas…
Optimizing the physical data storage and retrieval of data are two key database management problems. In this paper, we propose a language that can express a wide range of physical database layouts, going well beyond the row- and column-based methods that are widely used in database management systems. We use deductive synthesis to turn a high-level relational representation of a database query into a highly optimized low-level implementation which operates on a specialized layout of the dataset. We build a compiler for this language and conduct experiments using a popular database benchmark, w…
Conventional object-stores are built on top of traditional OS storage stack, where I/O requests typically transfers through multiple hefty and redundant layers. The complexity of object management has grown dramatically with the ever increasing requirements of performance, consistency and fault-tolerance from storage subsystems. Simply stated, more number of intermediate layers are encountered in the I/O data path, with each passing layer adding its own syntax and semantics. Thereby increasing the overheads of request processing. In this paper, through comprehensive under-the-hood analysis of …
Applications running on parallel systems often need to join a streaming relation or a stored relation with data indexed in a parallel data storage system. Some applications also compute UDFs on the joined tuples. The join can be done at the data storage nodes, corresponding to reduce side joins, or by fetching data from the storage system to compute nodes, corresponding to map side join. Both may be suboptimal: reduce side joins may cause skew, while map side joins may lead to a lot of data being transferred and replicated. In this paper, we present techniques to make runtime decisions between…
Big data management is a reality for an increasing number of organizations in many areas and represents a set of challenges involving big data modeling, storage and retrieval, analysis and visualization. However, technological resources, people and processes are crucial to facilitate the management of big data in any kind of organization, allowing information and knowledge from a large volume of data to support decision-making. Big data management can be supported by these three dimensions: technology, people and processes. Hence, this article discusses these dimensions: the technological dime…
