Figure database ｜ Nepal graph v3.1.0 performance report

This article was first published in Nebula Graph Community official account

Department of literature Nebula Graph Distribution version v3.1.0 Performance test report of .

Contents of this article

• Test environment
• Test data
  • About LDBC-SNB
• Test instructions
• Test cases and results
  • MatchTest1
  • MatchTest2
  • MatchTest3
  • MatchTest4
  • MatchTest5
• 3.1.0 vs 3.0.0（Baseline）
  • MatchTest1
  • MatchTest2
  • MatchTest3
  • MatchTest4
  • MatchTest5

Test conclusion

stay v3.1.0 In the version , Query and data import performance is basically the same as v3.0.0 flat （ Reference resources ：v3.0.0 Performance report ）.MATCH Statement is optimized for attribute reading , Corresponding use cases are added in this test , Performance comparison v3.0.0 A big increase .

Test environment

Both the server and the pressure measuring machine are physical machines

• Be careful ： server setting CPU by Performance Pattern .

Test data

The test data are LDBC-SNB SF100 Data sets ,SF100 The data set size is 100G, share 282,386,021 A point and 1,775,513,185 side . The number of graph space partitions used for the test is 24, Replications for 3.

About LDBC-SNB

Associated data benchmarking Committee （LDBC,Linked Data Benchmark Council）, The picture is （Graph） and RDF Benchmark guide setters for data management . Social networking benchmark （SNB,Social Network Benchmark） It's the association data benchmark Committee （LDBC） Developed software benchmark （Benchmark） One of . About LDBC-SNB Data sets , Please refer to the following documents for details ：

• LDBC_SNB_SF100：https://ldbcouncil.org/ldbc_snb_docs/ldbc-snb-specification.pdf
• 24 Partitions：https://github.com/ldbc/ldbc_snb_docs
• 3 Replica Factors：https://github.com/ldbc/ldbc_snb_datagen_spark

Test instructions

1. The use of pressure measuring tools is based on Go Linguistic k6, Please refer to k6 Official website ; The client uses nebula-go
2. Of the abscissa axis in the chart “50_vu”、“100_vu” Isochronous “vu” It means k6 Concepts used “virtual user”, That is, the number of concurrency in the performance test ;50_vu Express 50 Concurrent users ,100_vu Express 100 Concurrent users , And so on …
3. The performance baseline uses the officially released 3.0.0 edition
4. ResponseTime = Latency（ The processing time of the server ）+ The length of time for the network to return the result + The time taken for the client to deserialize the result
5. Parameter description
   • QPS namely Throughput rate
   • Latency namely The server takes time
   • ResponseTime namely Client time consuming

Test cases and results

Only the newly added match The test case

• QPS namely Throughput rate
• Latency namely The server takes time
• ResponseTime namely Client time consuming

MatchTest1

match (v:Person) where id(v) == {} return count(v.Person.firstName)

MatchTest2

match (v:Person)-[e:KNOWS]-(v2) where id(v) == {} and v2.Person.locationIP != 'yyy' return length(v.Person.browserUsed) + length(v2.Person.gender)

MatchTest3

match (v:Person)-[e:KNOWS]-(v2) where id(v) == {} and v2.Person.locationIP != 'yyy' with v, v2 as v3 return length(v.Person.browserUsed) + (v3.Person.gender)

MatchTest4

MATCH (m)-[:KNOWS]-(n) WHERE id(m)=={} OPTIONAL MATCH (n)<-[:KNOWS]-(l) RETURN length(m.Person.lastName) AS n1, length(n.Person.lastName) AS n2, l.Person.creationDate AS n3 ORDER BY n1, n2, n3 LIMIT 10

MatchTest5

MATCH (m)-[:KNOWS]-(n) WHERE id(m)=={} MATCH (n)-[:KNOWS]-(l) WITH m AS x, n AS y, l RETURN x.Person.firstName AS n1, y.Person.firstName AS n2, CASE WHEN l.Person.firstName is not null THEN l.Person.firstName WHEN l.Person.gender is not null THEN l.Person.birthday ELSE 'null' END AS n3 ORDER BY n1, n2, n3 LIMIT 10

v3.1.0 vs v3.0.0（Baseline）

Select the following data P99 value .

MatchTest1

match (v:Person) where id(v) == {} return count(v.Person.firstName)

MatchTest2

match (v:Person)-[e:KNOWS]-(v2) where id(v) == {} and v2.Person.locationIP != 'yyy' return length(v.Person.browserUsed) + length(v2.Person.gender)

MatchTest3

match (v:Person)-[e:KNOWS]-(v2) where id(v) == {} and v2.Person.locationIP != 'yyy' with v, v2 as v3 return length(v.Person.browserUsed) + (v3.Person.gender)

MatchTest4

MATCH (m)-[:KNOWS]-(n) WHERE id(m)=={} OPTIONAL MATCH (n)<-[:KNOWS]-(l) RETURN length(m.Person.lastName) AS n1, length(n.Person.lastName) AS n2, l.Person.creationDate AS n3 ORDER BY n1, n2, n3 LIMIT 10

MatchTest5

MATCH (m)-[:KNOWS]-(n) WHERE id(m)=={} MATCH (n)-[:KNOWS]-(l) WITH m AS x, n AS y, l RETURN x.Person.firstName AS n1, y.Person.firstName AS n2, CASE WHEN l.Person.firstName is not null THEN l.Person.firstName WHEN l.Person.gender is not null THEN l.Person.birthday ELSE 'null' END AS n3 ORDER BY n1, n2, n3 LIMIT 10

above , Welcome to GitHub Experience v3.1.0 edition ,GitHub Address ：https://github.com/vesoft-inc/nebula/releases/tag/v3.1.0

Communication graph database technology ？ Join in Nebula Communication group please first Fill in your Nebula Business card ,Nebula The little assistant will pull you into the group ~~