Graph Database Benchmark Reports

OCTOBER 2020

Linked Data Benchmark Council Social Network Benchmark (4.8TB raw dataset)

In a recent study, we measured TigerGraph’s performance using the respected Linked Data Benchmark Council (LDBC) Social Network Benchmark (SNB) Scale-Factor 10K dataset  (8.86B vertices, 61.77B edges, 4.8TB raw data). We tested TigerGraph’s performance using three types of queries on a distributed cluster: 

  • IS Workload—all queries were answered in one to three seconds. The cluster size did not noticeably influence performance, since only a small part of the graph is touched. 
  • IC Workload—all queries were answered in three to nine seconds. The cluster size does not influence the performance much, since only a small part of the graph is touched.
  • BI Workload—the majority of OLAP-style iterative and/or deep-link graph queries were answered in under one minute. The majority of queries exhibited linear scale-out performance.

Each query was performed three times, and the median of the elapsed times presented as the final latency time. Each query was performed on clusters of 12, 18, and 24 machines, respectively. 

This study clearly demonstrates TigerGraph’s ability to run deep-link OLAP-style aggregation queries on a cluster of commodity machines with a graph of almost nine billion vertices and over 60 billion edges and returns results in under a minute. No other graph database vendor or relational database vendor has demonstrated equivalent analytical capabilities. 

GitHub Location with datasets as well as procedure to reproduce

benchmarking tigergraph collateral

Third Party Benchmark:
Neo4j vs TigerGraph

July 2019 In-Depth Benchmarking of Graph Database Systems using the Linked Data Benchmark Council (LDBC) Social Network Benchmark (SNB).  

Graph Database Benchmark Report

This benchmark compares TigerGraph to Neo4j, Amazon Neptune, JanusGraph and ArangoDB in the following categories:

Queries: For 2-hop path queries, TigerGraph is 40x to 337x faster than other graph databases.

Storage: When comparing storage requirements for the same raw data, other graph databases need5x to 13x more disk space compared to TigerGraph.

Loading: TigerGraph loads data1.8x to 58x faster than other graph databases.

Scale: TigerGraph scales almost linearly with additional machines, achieving 6.7x speedup with 8 machines for the computationally intensive PageRank algorithm. Neo4j and Amazon Neptune cannot partition a graph across multiple machines for the versions tested, thus could not be tested for this part.

Click below for the benchmark summary or download the full report.