Property graphs are a common form of linked data, with path queries used to traverse and explore them for enterprise transactions and mining. Temporal property graphs are a recent variant where time is a first-class entity to be queried over, and their properties and structure vary over time. These are seen in social, telecom, transit and epidemic networks. However, current graph databases and query engines have limited support for temporal relations among graph entities, no support for time-varying entities and/or do not scale on distributed resources. We address this gap by extending a linear path query model over property graphs to include intuitive temporal predicates and aggregation operators over temporal graphs. We design a distributed execution model for these temporal path queries using the interval-centric computing model, and develop a novel cost model to select an efficient execution plan from several. We perform detailed experiments of our Granite distributed query engine using both static and dynamic temporal property graphs as large as 52M vertices, 218M edges and 325M properties, and a 1600-query workload, derived from the LDBC benchmark. We often offer sub-second query latencies on a commodity cluster, which is 149x-1140x faster compared to industry-leading Neo4J shared-memory graph database and the JanusGraph / Spark distributed graph query engine. Granite also completes 100% of the queries for all graphs, compared to only 32-92% workload completion by the baseline systems. Further, our cost model selects a query plan that is within 10% of the optimal execution time in 90% of the cases. Despite the irregular nature of graph processing, we exhibit a weak-scaling efficiency >= 60% on 8 nodes and >= 40% on 16 nodes, for most query workloads.
The National Archives（国家档案馆）；University of Technology Sydney（悉尼科技大学）
When data stores and users are distributed geographically, it is essential to organize distributed data cache points at ideal locations to minimize data transfers. To answer this, we are developing an adaptive distributed data caching framework that can identify suitable data chunks to cache and move across a network of community cache locations.
Graph query services (GQS) are widely used today to interactively answer graph traversal queries on large-scale graph data. Existing graph query engines focus largely on optimizing the latency of a single query. This ignores significant challenges posed by GQS, including fine-grained control and scheduling during query execution, as well as performance isolation and load balancing in various levels from across user to intra-query. To tackle these control and scheduling challenges, we propose a novel scoped dataflow for modeling graph traversal queries, which explicitly exposes concurrent execu…
Regular Path Queries (RPQs) are a type of graph query where answers are pairs of nodes connected by a sequence of edges matching a regular expression. We study the techniques to process such queries on a distributed graph of data. While many techniques assume the location of each data element (node or edge) is known, when the components of the distributed system are autonomous, the data will be arbitrarily distributed. As the different query processing strategies are equivalently costly in the worst case, we isolate query-dependent cost factors and present a method to choose between strategies…
As RDF becomes more widely established and the amount of linked data is rapidly increasing, the efficient querying of large amount of data becomes a significant challenge. In this paper, we propose a family of algorithms for querying large amount of linked data in a distributed manner. These query evaluation algorithms are independent of the way the data is stored, as well as of the particular implementation of the query evaluation. We then use the MapReduce paradigm to present a distributed implementation of these algorithms and experimentally evaluate them, although the algorithms could be s…
We address the problem of answering queries over a distributed information system, storing objects indexed by terms organized in a taxonomy. The taxonomy consists of subsumption relationships between negation-free DNF formulas on terms and negation-free conjunctions of terms. In the first part of the paper, we consider the centralized case, deriving a hypergraph-based algorithm that is efficient in data complexity. In the second part of the paper, we consider the distributed case, presenting alternative ways implementing the centralized algorithm. These ways descend from two basic criteria: di…
Most distributed storage systems provide limited abilities for querying data by attributes other than their primary keys. Supporting efficient search on secondary attributes is challenging as applications pose varying requirements to query processing systems, and no single system design can be suitable for all needs. In this paper, we show how to overcome these challenges in order to extend distributed data stores to support queries on secondary attributes. We propose a modular architecture that is flexible and allows query processing systems to make trade-offs according to different use case …
Efficient execution of SPARQL queries over large RDF datasets is a topic of considerable interest due to increased use of RDF to encode data. Most of this work has followed either relational or graph-based approaches. In this paper, we propose an alternative query engine, called gSmart, based on matrix algebra. This approach can potentially better exploit the computing power of high-performance heterogeneous architectures that we target. gSmart incorporates: (1) grouped incident edge-based SPARQL query evaluation, in which all unevaluated edges of a vertex are evaluated together using a series…
Modern database clusters entail two levels of networks: connecting CPUs and NUMA regions inside a single server in the small and multiple servers in the large. The huge performance gap between these two types of networks used to slow down distributed query processing to such an extent that a cluster of machines actually performed worse than a single many-core server. The increased main-memory capacity of the cluster remained the sole benefit of such a scale-out. The economic viability of high-speed interconnects such as InfiniBand has narrowed this performance gap considerably. However, Infini…
Querying graph data with low latency is an important requirement in application domains such as social networks and knowledge graphs. Graph queries perform multiple hops between vertices. When data is partitioned and stored across multiple servers, queries executing at one server often need to hop to vertices stored by another server. Such distributed traversals represent a performance bottleneck for low-latency queries. To reduce query latency, one can replicate remote data to make distributed traversals unnecessary, but replication is expensive and should be minimized. In this paper, we intr…
W3C's XML-Query language offers a powerful instrument for information retrieval on XML repositories. This article describes an implementation of this retrieval in a real world's scenario. Distributed XML-Query processing reduces load on every single attending node to an acceptable level. The network allows every participant to control their computing load themselves. Furthermore XML-repositories may stay at the rights holder, so every Data-Provider can decide, whether to process critical queries or not. If Data-Providers keep redundant information, this distributed network improves reliability…
Many modern applications require the evaluation of analytical queries on large amounts of data. Such queries entail joins and heavy aggregations that often include user-defined functions (UDFs). The most efficient way to process these specific type of queries is using tree execution plans. In this work, we develop an engine for analytical query processing and a suite of specialized techniques that collectively take advantage of the tree form of such plans. The engine executes these tree plans in an elastic IaaS cloud infrastructure and dynamically adapts by allocating and releasing pertinent r…
Increasing need for large-scale data analytics in a number of application domains has led to a dramatic rise in the number of distributed data management systems, both parallel relational databases, and systems that support alternative frameworks like MapReduce. There is thus an increasing contention on scarce data center resources like network bandwidth; further, the energy requirements for powering the computing equipment are also growing dramatically. As we show empirically, increasing the execution parallelism by spreading out data across a large number of machines may achieve the intended…
A1 is an in-memory distributed database used by the Bing search engine to support complex queries over structured data. The key enablers for A1 are availability of cheap DRAM and high speed RDMA (Remote Direct Memory Access) networking in commodity hardware. A1 uses FaRM as its underlying storage layer and builds the graph abstraction and query engine on top. The combination of in-memory storage and RDMA access requires rethinking how data is allocated, organized and queried in a large distributed system. A single A1 cluster can store tens of billions of vertices and edges and support a throug…
We propose techniques for processing SPARQL queries over a large RDF graph in a distributed environment. We adopt a "partial evaluation and assembly" framework. Answering a SPARQL query Q is equivalent to finding subgraph matches of the query graph Q over RDF graph G. Based on properties of subgraph matching over a distributed graph, we introduce local partial match as partial answers in each fragment of RDF graph G. For assembly, we propose two methods: centralized and distributed assembly. We analyze our algorithms from both theoretically and experimentally. Extensive experiments over both r…
As data sets grow in size, analytics applications struggle to get instant insight into large datasets. Modern applications involve heavy batch processing jobs over large volumes of data and at the same time require efficient ad-hoc interactive analytics on temporary data. Existing solutions, however, typically focus on one of these two aspects, largely ignoring the need for synergy between the two. Consequently, interactive queries need to re-iterate costly passes through the entire dataset (e.g., data loading) that may provide meaningful return on investment only when data is queried over a l…
The increasing amount of Linked Data and its inherent distributed nature have attracted significant attention throughout the research community and amongst practitioners to search data, in the past years. Inspired by research results from traditional distributed databases, different approaches for managing federation over SPARQL Endpoints have been introduced. SPARQL is the standardised query language for RDF, the default data model used in Linked Data deployments and SPARQL Endpoints are a popular access mechanism provided by many Linked Open Data (LOD) repositories. In this paper, we initial…
As the volume of the RDF data becomes increasingly large, it is essential for us to design a distributed database system to manage it. For distributed RDF data design, it is quite common to partition the RDF data into some parts, called fragments, which are then distributed. Thus, the distribution design consists of two steps: fragmentation and allocation. In this paper, we propose a method to explore the intrinsic similarities among the structures of queries in a workload for fragmentation and allocation, which aims to reduce the number of crossing matches and the communication cost during SP…
Distributed heterogeneous data sources need to be queried uniformly using global schema. Query on global schema is reformulated so that it can be executed on local data sources. Constraints in global schema and mappings are used for source selection, query optimization,and querying partitioned and replicated data sources. The provided system is all XML-based which poses query in XML form, transforms, and integrates local results in an XML document. Contributions include the use of constraints in our existing global schema which help in source selection and query optimization, and a global quer…
Similarity search is a core component in various applications such as image matching, product recommendation and low-shot classification. However, single machine solutions are usually insufficient due to the large cardinality of modern datasets and stringent latency requirement of on-line query processing. We present Pyramid, a general and efficient framework for distributed similarity search. Pyramid supports search with popular similarity functions including Euclidean distance, angular distance and inner product. Different from existing distributed solutions that are based on KD-tree or loca…
Huge amounts of data being generated continuously by digitally interconnected systems of humans, organizations and machines. Data comes in variety of formats including structured, unstructured and semi-structured, what makes it impossible to apply the same standard approaches, techniques and algorithms to manage and process this data. Fortunately, the enterprise level distributed platform named Hadoop Ecosystem exists. This paper explores Apache Hive component that provides full stack data managements functionality in terms of Data Definition, Data Manipulation and Data Processing. Hive is a d…
In the age of big data, more and more applications need to query and analyse large volumes of continuously updated data in real-time. In response, cloud-scale storage systems can extend their interface that allows fast lookups on the primary key with the ability to retrieve data based on non-primary attributes. However, the need to ingest content rapidly and make it searchable immediately while supporting low-latency, high-throughput query evaluation, as well as the geo-distributed nature and weak consistency guarantees of modern storage systems pose several challenges to the implementation of…
Partial evaluation has recently been used for processing SPARQL queries over a large resource description framework (RDF) graph in a distributed environment. However, the previous approach is inefficient when dealing with complex queries. In this study, we further improve the "partial evaluation and assembly" framework for answering SPARQL queries over a distributed RDF graph, while providing performance guarantees. Our key idea is to explore the intrinsic structural characteristics of partial matches to filter out irrelevant partial results, while providing performance guarantees on a network…
This paper presents a distributed search engine based on semantic P2P Networks. The user's computers join the domains in which user wants to share information in semantic P2P networks which is domain specific virtual tree (VIRGO ). Each user computer contains search engine which indexes the domain specific information on local computer or Internet. We can get all search information through P2P message provided by all joined computers. By companies' effort, we have implemented a prototype of distributed search engine, which demonstrates easily retrieving domain-related information provided by j…
Massively scalable web applications encounter a fundamental tension in computing between "performance" and "correctness": performance is often addressed by using a large and therefore distributed machine where programs are multi-threaded and interruptible, whereas correctness requires data invariants to be maintained with certainty. A solution to this problem is "transactions" [Gray-Reuter]. Some distributed systems such as Google App Engine [http://code.google.com/appengine/docs/] provide transaction semantics but only for functions that access one of a set of predefined local regions of the …
Distributed frameworks are gaining increasingly widespread use in applications that process large amounts of data. One important example application is large scale similarity search, for which Locality Sensitive Hashing (LSH) has emerged as the method of choice, specially when the data is high-dimensional. At its core, LSH is based on hashing the data points to a number of buckets such that similar points are more likely to map to the same buckets. To guarantee high search quality, the LSH scheme needs a rather large number of hash tables. This entails a large space requirement, and in the dis…
The rule technological landscape is becoming ever more complex, with an extended number of specifications and products. It is therefore becoming increasingly difficult to integrate rule-driven components and manage interoperability in multi-rule engine environments. The described work presents the possibility to provide a common interface for rule-driven components in a distributed system. The authors' approach leverages on a set of discovery protocol, rule interchange and user interface to alleviate the environment's complexity.
This paper proposes Kudu, a distributed execution engine with a well-defined abstraction that can be integrated with existing single-machine graph pattern mining (GPM) systems to provide efficiency and scalability at the same time. The key novelty is the extendable embedding abstraction which can express pattern enumeration algorithms, allow fine-grained task scheduling, and enable low-cost GPM-specific data reuse to reduce communication cost. The effective BFSDFS hybrid exploration generates sufficient concurrent tasks for communication-computation overlapping with bounded memory consumption.…
ASYNC is a framework that supports the implementation of asynchrony and history for optimization methods on distributed computing platforms. The popularity of asynchronous optimization methods has increased in distributed machine learning. However, their applicability and practical experimentation on distributed systems are limited because current bulk-processing cloud engines do not provide a robust support for asynchrony and history. With introducing three main modules and bookkeeping system-specific and application parameters, ASYNC provides practitioners with a framework to implement async…
Blockchain is one of the most popular distributed ledger technologies. It can solve the trust issue among enterprises. Hyperledger Fabric is a permissioned blockchain aiming at enterprise-grade business applications. However, compared to traditional distributed database solutions, one issue of blockchain based application development is the limited data access. For Fabric, the ledger data can only be retrieved by limited interfaces provided by Fabric SDKs or chaincode. In order to meet the requirements of data query and provide flexible query functions for real applications built on Fabric, th…
This paper describes the architecture of MOSE (My Own Search Engine), a scalable parallel and distributed engine for searching the web. MOSE was specifically designed to efficiently exploit affordable parallel architectures, such as clusters of workstations. Its modular and scalable architecture can easily be tuned to fulfill the bandwidth requirements of the application at hand. Both task-parallel and data-parallel approaches are exploited within MOSE in order to increase the throughput and efficiently use communication, storing and computational resources. We used a collection of html docume…
In the pooled data problem we are given a set of $n$ agents, each of which holds a hidden state bit, either $0$ or $1$. A querying procedure returns for a query set the sum of the states of the queried agents. The goal is to reconstruct the states using as few queries as possible. In this paper we consider two noise models for the pooled data problem. In the noisy channel model, the result for each agent flips with a certain probability. In the noisy query model, each query result is subject to random Gaussian noise. Our results are twofold. First, we present and analyze for both error models …
