Update-intensive Workloads Research Articles

Eukv: Enabling Efficient Updates for Hybrid PM-DRAM Key-Value Store

Key-value store, a fundamental component in a variety of modern data-intensive applications, can benefit from the emerging persistent memory (PM) to achieve high performance. Recent research proposes hybrid PM-DRAM key-value stores, which persist key-value pairs to PM in a log-structured approach for efficient storage and maintain a volatile hash index in DRAM for fast indexing. However, they fail to achieve high performance under update-intensive workloads due to the unawareness of PM’s characteristics. We propose Eukv, a hybrid PM-DRAM key-value store that supports efficient updates. Eukv (1) leverages out-of-place updates and lazy deletions to reduce small random PM reads and writes, (2) performs concurrency control only in a volatile hash index to further reduce small random PM reads and writes introduced by persistent lock operations, (3) uses cacheline-aligned writes to take full advantage of PM’s write performance, (4) improves garbage collection efficiency through hot and cold data separation, (5) employs multi-threaded garbage collection technology to reduce the impact of inefficient garbage collection on updates at high-capacity utilization. We conduct extensive evaluations on an 18-core machine equipped with Intel Optane DC Persistent Memory Modules. Experimental results demonstrate that Eukv obtains up to 5.6× speedup than the state-of-the-art hybrid PM-DRAM key-value store.

Validity Tracking Based Log Management for In-Memory Databases

With in-memory databases (IMDBs), where all data sets reside in main memory for fast processing speed, logging and checkpointing are essential for achieving persistence in data. Logging of IMDBs has evolved to reduce run-time overhead to suit the systems, but this causes an increase in recovery time. Checkpointing technique compensates for these problems with logging, but existing schemes often incur high costs due to reduced system throughput, increased latency, and increased memory usage. In this paper, we propose a checkpointing scheme using validity tracking-based compaction (VTC), the technique that tracks the validity of logs in a file and removes unnecessary logs. The proposed scheme shows extremely low memory usage compared to existing checkpointing schemes, which use consistent snapshots. Our experiments demonstrate that checkpoints using consistent snapshot increase memory footprint by up to two times in update-intensive workloads. In contrast, our proposed VTC only requires 2% additional memory for checkpointing. That means the system can use most of its memory to store data and process transactions.

Deduplication Adapted CaseDB for Edge Computing

Log-structured merge-tree (LSM-tree) family key-value stores are becoming the databases most in demand for big data systems. They provide an easy-to-implement interface, and they automatically perform garbage collection by applying a compaction procedure over the multilevel structure. CaseDB offers various advantages by reducing write amplification considerably, using a metadata compaction technique. However, it suffers from a space amplification problem in update-intensive workloads. As an implementation of the LSM-tree structure, CaseDB refuses to instantly perform deletes, but delays them for the compaction process, resulting in an increasing amount of deprecated data. This paper proposes a deduplication extended compaction method for CaseDB. It scans for duplicated keys within the compaction method and removes the old values. Experiment results show that the proposed technique offers various threshold values of deduplication for different balances between space amplification and write amplification.

An Ant Colony Optimization Based Data Update Scheme for Distributed Erasure-Coded Storage Systems

Owing to the high availability and space-efficiency of erasure codes, they have become the de facto standard to provide data durability in large scale distributed storage systems. The update-intensive workloads of erasure codes lead to a large amount of data transmission and I/O. As a result, it becomes a major challenge to reduce the amount of data transmission and optimize the use of existing network resources so that the update efficiency of the erasure codes could be improved. However, very little research has been done to optimize the update efficiency of the erasure codes under multiple QoS metrics. In this paper, our proposed update scheme, the Ant Colony Optimization based multiple data nodes Update Scheme (ACOUS) employs a two-stage rendezvous data update procedure to optimize the multiple data nodes updates. Specifically, the two-stage rendezvous data update procedure performs the data delta collection and the parity delta distribution based on a multi-objective update tree which is built by the ant colony optimization routing algorithm. Under typical data center network topologies, extensive experimental results show that, compared to the traditional TA-Update scheme, our scheme is able to achieve a 26% to 37% reduction of update delay with convergence guarantee at the cost of negligible computation overhead.

Optimal column layout for hybrid workloads

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.

Enabling Efficient Updates in KV Storage via Hashing

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 grouping , which deterministically maps values to storage space to make both updates and GC efficient. We further relax the restriction of such deterministic mappings via simple but useful design extensions. We extensively evaluate various design aspects of HashKV. We show that HashKV achieves 4.6× update throughput and 53.4% less write traffic compared to the current KV separation design. In addition, we demonstrate that we can integrate the design of HashKV with state-of-the-art KV stores and improve their respective performance.

Collaborative Compaction Optimization System using Near-Data Processing for LSM-tree-based Key-Value Stores

Log-structured merge tree (LSM-tree) based key–value stores are widely employed in large-scale storage systems. In compaction, high-level sorted string table files (i.e., SSTables) are merged with low-level overlapping key ranges and sorted for data queries. However, the compaction process incurs write amplification, which degrades system performance particularly under update-intensive workloads. Current optimizations mostly focus on reducing the overload of compaction in the host but rarely exploit parallelisms between the host and the device to fully utilize computing resources in the entire system for optimizing compaction performance. In this study, we propose Co-KV, a Collaborative Key-Value store, to improve compaction performance in LSM-tree-based key–value stores. Co-KV is based on a near-data processing (i.e., NDP) model-enabled storage device. Co-KV exhibits the following advantages: (1) it reduces write amplification and host-side CPU costs using a compaction offloading scheduling between a host computer and an NDP-enabled storage device; (2) it relieves the overload associated with data transfer between the host and the storage device; and (3) it improves the compaction of LSM-tree based key–value stores under update-intensive workloads.We employed an Open Ethernet Driver (OED), which is a real-world NDP platform as the testbed for our experiments. Extensive db_bench evaluations demonstrate that Co-KV achieves overall throughput improvements of approximately 1.75x, CPU cost reductions of approximately 68.1%, and write amplification reductions by up to 50.0% over the state-of-the-art LevelDB. Under YCSB workloads, Co-KV increases throughput by 1.7x ∼ 1.9x while decreasing the write amplification and average latency by up to 50.0% and 46.3%, respectively.

LB-Grid: An SSD efficient Grid File

Recent advances in non-volatile memory technology have led to the introduction of solid state drives (SSD). NVMe SSDs are the latest development in flash based solid state drives and they were designed as a means of low latency and high bandwidth. Many research studies seek for taking advantage of this new technology to accelerate data management. Multidimensional indexes are fundamental for the efficiency of spatial query processing. In this work, we study the implication of high performance NVMe drives on spatial indexing. More specifically, we present an in-depth performance analysis of the Grid File in flash storage and we introduce LB-Grid, a write efficient variant of Grid File for flash based solid state drives. We present new query algorithms for both LB-Grid and Grid File that exploit the high internal parallelism and I/O bandwidth of NVMe SSDs. Experimental results unveil the efficiency of the proposed algorithms. Utilizing a test set of 500M points, LB-Grid appears to be up to 2.26 times faster than Grid File, up to 5.5 times faster than the R∗-tree, and up to 3.3 times faster than the FAST-Rtree in update intensive workloads. On the other hand, the Grid File presents better performance in read intensive workloads; exploiting a batch read operation, it achieves a speedup up to 10.2x in range queries, up to 1.56x in kNN and 4.6x in group point queries.

Parallel replication across formats for scaling out mixed OLTP/OLAP workloads in main-memory databases

Modern in-memory database systems are facing the need of efficiently supporting mixed workloads of OLTP and OLAP. A conventional approach to this requirement is to rely on ETL-style, application-driven data replication between two very different OLTP and OLAP systems, sacrificing real-time reporting on operational data. An alternative approach is to run OLTP and OLAP workloads in a single machine, which eventually limits the maximum scalability. In order to tackle this challenging problem, we propose a novel database replication architecture called HANA Asynchronous Parallel Table Replication (ATR). ATR supports OLTP workloads in one primary machine, while it supports heavy OLAP workloads in replicas. Here, row store formats can be used for OLTP transactions at the primary, while column store formats are used for OLAP analytical queries at the replicas. ATR is designed to support elastic scalability of OLAP query performance, while it minimizes the overhead for transaction processing at the primary and minimizes CPU consumption for replayed transactions at the replicas. ATR employs a novel optimistic lock-free parallel log replay scheme which exploits characteristics of multi-version concurrency control (MVCC) to enable real-time reporting by minimizing the propagation delay between the primary and replicas. It supports adaptive query routing depending on its predefined acceptable staleness range. Through extensive experiments with a concrete implementation available in a commercial product, we demonstrate that ATR achieves sub-second visibility delay even for update-intensive workloads, providing scalable OLAP performance without notable overhead to the primary. In addition, with extension of ATR to eager parallel replication, we demonstrate how the parallel log replay and its log-less replica recovery mechanisms improve run-time transaction performance under eager replication.

<italic>DStore</italic>: A Holistic Key-Value Store Exploring Near-Data Processing and On-Demand Scheduling for Compaction Optimization

Log-structured merge tree (LSM-tree)-based key-value stores are widely deployed in large-scale storage systems. The underlying reason is that the traditional relational databases cannot reach the high performance required by big-data applications. As high-throughput alternatives to relational databases, LSM-tree-based key-value stores can support high-throughput write operations and provide high sequential bandwidth in storage systems. However, the compaction process triggers write amplification and is confronted with the degraded write performance, especially under update-intensive workloads. To address this issue, we design a holistic key-value store to explorer near-data processing (NDP) and on-demand scheduling for compaction optimization in an LSM-tree key-value store, named DStore. DStore makes full use of various computing capacities in the host-side and device-side subsystems. DStore dynamically divides the whole host-side compaction tasks into the above two-side subsystems according to two-side different computing capabilities. Meanwhile, the device must be featured with an NDP model. The divided compaction tasks are performed by the host and the device in parallel. In DStore, the NDP-based devices exhibit low-latency and high-bandwidth performance, thus facilitating key-value stores. DStore not only accomplishes compaction for key-value stores but also improves the system performance. We implement our DStore prototype in a real-world platform, and different kinds of testbeds are employed in our experiment. LevelDB and a static compaction optimization using the NDP model (called Co-KV) are used to compare with the DStore in our evaluation. Results show that DStore achieves about $3.7 \times $ performance improvement over LevelDB under the db_bench workload. In addition, DStore-enabled key-value stores outperform LevelDB by a factor of about $3.3 \times $ and 77% in terms of throughput and latency under YCSB benchmark, respectively.

Parallel replication across formats in SAP HANA for scaling out mixed OLTP/OLAP workloads

Modern in-memory database systems are facing the need of efficiently supporting mixed workloads of OLTP and OLAP. A conventional approach to this requirement is to rely on ETL-style, application-driven data replication between two very different OLTP and OLAP systems, sacrificing real-time reporting on operational data. An alternative approach is to run OLTP and OLAP workloads in a single machine, which eventually limits the maximum scalability of OLAP query performance. In order to tackle this challenging problem, we propose a novel database replication architecture called Asynchronous Parallel Table Replication (ATR). ATR supports OLTP workloads in one primary machine, while it supports heavy OLAP workloads in replicas. Here, row-store formats can be used for OLTP transactions at the primary, while column-store formats are used for OLAP analytical queries at the replicas. ATR is designed to support elastic scalability of OLAP query performance while it minimizes the overhead for transaction processing at the primary and minimizes CPU consumption for replayed transactions at the replicas. ATR employs a novel optimistic lock-free parallel log replay scheme which exploits characteristics of multi-version concurrency control (MVCC) in order to enable real-time reporting by minimizing the propagation delay between the primary and replicas. Through extensive experiments with a concrete implementation available in a commercial database system, we demonstrate that ATR achieves sub-second visibility delay even for update-intensive workloads, providing scalable OLAP performance without notable overhead to the primary.

Compaction management in distributed key-value datastores

Compactions are a vital maintenance mechanism used by datastores based on the log-structured merge-tree to counter the continuous buildup of data files under update-intensive workloads. While compactions help keep read latencies in check over the long run, this comes at the cost of significantly degraded read performance over the course of the compaction itself. In this paper, we offer an in-depth analysis of compaction-related performance overheads and propose techniques for their mitigation. We offload large, expensive compactions to a dedicated compaction server to allow the datastore server to better utilize its resources towards serving the actual workload. Moreover, since the newly compacted data is already cached in the compaction server's main memory, we fetch this data over the network directly into the datastore server's local cache, thereby avoiding the performance penalty of reading it back from the filesystem. In fact, pre-fetching the compacted data from the remote cache prior to switching the workload over to it can eliminate local cache misses altogether. Therefore, we implement a smarter warmup algorithm that ensures that all incoming read requests are served from the datastore server's local cache even as it is warming up. We have integrated our solution into HBase, and using the YCSB and TPC-C benchmarks, we show that our approach significantly mitigates compaction-related performance problems. We also demonstrate the scalability of our solution by distributing compactions across multiple compaction servers.

Improving Update-Intensive Workloads on Flash Disks through Exploiting Multi-Chip Parallelism

Solid state drives (SSDs), or flash disks have been considered as ideal storage for various data-intensive workloads, because of the low random access latency and the intra-disk multi-chip parallelism. However, due to inherent nature of flash memories, update-intensive workloads cause the flash disk fragmented, and trigger costly internal activities such as cleaning and wear leveling. We use database transaction processing as a motivating update-intensive workload. Our studies based on a flash disk simulator as well as flash disks show that, these activities result in significant overhead to the I/O response time and system throughput. To resolve the impact of internal activities, we propose dynamic page replications to exploit the multi-chip parallelism on the flash disk. Specifically, we replicate the frequently blocked data pages to improve the data availability even when internal activities block the request. To reduce the overhead of replications, we take advantage of the idle periods in the flash chips for the I/O operations by writes to replicas or reads from replicas, and further develop a prediction model for the decisions on those I/O operations to minimize the interference to normal I/O operations. We evaluate our techniques with three public transaction benchmarks in the simulator as well as on the real flash disks. Our results demonstrate the effectiveness of our replication management on improving I/O response time and system throughput.

Database Services for Cloud Computing – An Overview

Cloud computing has revolutionized the way computinginfrastructure is abstracted and used. There is a proliferation ofnumber of applications which leverage various cloud platforms,resulting in a tremendous increase in the scale of data generated aswell as consumed by such applications. This paper reviews thefeatures of Cloud computing and then gives a survey of differentdatabase architecture for cloud computing. Scalable databasemanagement systems are a crucial part of the cloud infrastructurewhich includes both update intensive workloads and decisionsupport systems. The paper presents an organized picture of thechallenges and open issues pertaining to database managementsystems in developing and deploying internet scale applications inthe cloud environment. The typical properties of commerciallyavailable databases for cloud computing environment are alsobrought out.

An update-aware storage system for low-locality update-intensive workloads

Traditional storage systems provide a simple read/write interface, which is inadequate for low-locality update-intensive workloads because it limits the disk scheduling flexibility and results in inefficient use of buffer memory and raw disk bandwidth. This paper describes an update-aware disk access interface that allows applications to explicitly specify disk update requests and associate with such requests call-back functions that will be invoked when the requested disk blocks are brought into memory. Because call-back functions offer a continuation mechanism after retrieval of requested blocks, storage systems supporting this interface are given more flexibility in scheduling pending disk update requests. In particular, this interface enables a simple but effective technique called Batching mOdifications with Sequential Commit (BOSC), which greatly improves the sustained throughput of a storage system under low-locality update-intensive workloads. In addition, together with a space-efficient low-latency disk logging technique, BOSC is able to deliver the same durability guarantee as synchronous disk updates. Empirical measurements show that the random update throughput of a BOSC-based B+ tree is more than an order of magnitude higher than that of the same B+ tree implementation on a traditional storage system.

An update-aware storage system for low-locality update-intensive workloads

Traditional storage systems provide a simple read/write interface, which is inadequate for low-locality update-intensive workloads because it limits the disk scheduling flexibility and results in inefficient use of buffer memory and raw disk bandwidth. This paper describes an update-aware disk access interface that allows applications to explicitly specify disk update requests and associate with such requests call-back functions that will be invoked when the requested disk blocks are brought into memory. Because call-back functions offer a continuation mechanism after retrieval of requested blocks, storage systems supporting this interface are given more flexibility in scheduling pending disk update requests. In particular, this interface enables a simple but effective technique called Batching mOdifications with Sequential Commit (BOSC), which greatly improves the sustained throughput of a storage system under low-locality update-intensive workloads. In addition, together with a space-efficient low-latency disk logging technique, BOSC is able to deliver the same durability guarantee as synchronous disk updates. Empirical measurements show that the random update throughput of a BOSC-based B+ tree is more than an order of magnitude higher than that of the same B+ tree implementation on a traditional storage system.

Serializable snapshot isolation for replicated databases in high-update scenarios

Many proposals for managing replicated data use sites running the Snapshot Isolation (SI) concurrency control mechanism, and provide 1-copy SI or something similar, as the global isolation level. This allows good scalability, since only ww -conflicts need to be managed globally. However, 1-copy SI can lead to data corruption and violation of integrity constraints [5]. 1-copy serializability is the global correctness condition that prevents data corruption. We propose a new algorithm Replicated Serializable Snapshot Isolation (RSSI) that uses SI at each site, and combines this with a certification algorithm to guarantee 1-copy serializable global execution. Management of ww -conflicts is similar to what is done in 1-copy SI. But unlike previous designs for 1-copy serializable systems, we do not need to prevent all rw -conflicts among concurrent transactions. We formalize this in a theorem that shows that many rw -conflicts are indeed false positives that do not risk non-serializable behavior. Our proposed RSSI algorithm will only abort a transaction when it detects a well-defined pattern of two consecutive rw -edges in the serialization graph. We have built a prototype that integrates our RSSI with the existing open-source Postgres-R(SI) system. Our performance evaluation shows that there is a worst-case overhead of about 15% for getting full 1-copy serializability as compared to 1-copy SI in a cluster of 8 nodes, with our proposed RSSI clearly outperforming the previous work [6] for update-intensive workloads.