Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

The LDBC Social Network Benchmark

Renzo Angles, János Benjamin Antal, Alex Averbuch, Altan Birler, Peter Boncz, Márton Búr, Orri Erling, Andrey Gubichev, Vlad Haprian, Moritz Kaufmann, Josep Lluís Larriba Pey, Norbert Martínez, József Marton, Marcus Paradies, Minh-Duc Pham, Arnau Prat-Pérez, David Püroja, Mirko Spasić, Benjamin A. Steer, Dávid Szakállas, Gábor Szárnyas, Jack Waudby, Mingxi Wu, Yuchen Zhang

TL;DR

This document contains the definition of the Interactive Workload and the first draft of the Business Intelligence Workload, which consists of two workloads that focus on different functionalities: the Interactive workload (interactive transactional queries) and the Business Intelligence workload (analytical queries).

Abstract

The Linked Data Benchmark Council's Social Network Benchmark (LDBC SNB) is an effort intended to test various functionalities of systems used for graph-like data management. For this, LDBC SNB uses the recognizable scenario of operating a social network, characterized by its graph-shaped data. LDBC SNB consists of two workloads that focus on different functionalities: the Interactive workload (interactive transactional queries) and the Business Intelligence workload (analytical queries). This document contains the definition of both workloads. This includes a detailed explanation of the data used in the LDBC SNB, a detailed description for all queries, and instructions on how to generate the data and run the benchmark with the provided software.

The LDBC Social Network Benchmark

TL;DR

This document contains the definition of the Interactive Workload and the first draft of the Business Intelligence Workload, which consists of two workloads that focus on different functionalities: the Interactive workload (interactive transactional queries) and the Business Intelligence workload (analytical queries).

Abstract

The Linked Data Benchmark Council's Social Network Benchmark (LDBC SNB) is an effort intended to test various functionalities of systems used for graph-like data management. For this, LDBC SNB uses the recognizable scenario of operating a social network, characterized by its graph-shaped data. LDBC SNB consists of two workloads that focus on different functionalities: the Interactive workload (interactive transactional queries) and the Business Intelligence workload (analytical queries). This document contains the definition of both workloads. This includes a detailed explanation of the data used in the LDBC SNB, a detailed description for all queries, and instructions on how to generate the data and run the benchmark with the provided software.

Paper Structure

This paper contains 372 sections, 8 equations, 23 figures, 32 tables.

Table of Contents

  1. Introduction
  2. Motivation for the Benchmark
  3. Relevance to the Industry
  4. General Benchmark Overview
  5. Related Projects
  6. Participation of Industry and Academia
  7. Technical Report
  8. Benchmark Specification
  9. Overview
  10. Data sets and data generation
  11. Data Types
  12. Data Schema
  13. Entities (Nodes)
  14. Relations (Edges)
  15. Domain Concepts
  16. ...and 357 more sections

Figures (23)

  • Figure 1: High-level overview of the frameworks implementing each LDBC Social Network Benchmark workload. Legend: Software componentData artifact
  • Figure 2: UML class diagram-style depiction of the LDBC SNB graph schema. Note that the knows edges should be treated as undirected (but are serialized only in a single direction). The cardinality of the hasModerator edge has changed between version 1 (where it was exactly 1) and version 2 (where it is 0..1).
  • Figure 3: The Datagen generation process.
  • Figure 4: The power-law used to generate comments.
  • Figure 5: The distribution used to generate posts during flashmob events.
  • ...and 18 more figures