[Performance] Running LDBC CR9 in GAIA-X Quite Slow

[youyangy]

g.V($personId).out('knows').dedup().union(identity(), out('knows')).dedup().hasId(neq($personId)).as('friends').in('hasCreator').hasLabel('post').has('creationDate',lt($maxDate)).as('post').order().by('creationDate', desc).by('id', asc).limit(20).select('friends','post').by(valueMap('id', 'firstName', 'lastName')).by(valueMap('id', 'content', 'imageFile', 'creationDate'))

[longbinlai]

Could you please also include the benchmark dataset, machine configuration, as well as the time difference while compared to MG?

[youyangy]

Hardware Configurations ● cluster: an two nodes cluster ● memory: 503GB memory ● network: 20Gbps network ● cpu: two 16-core Intel(R) Xeon(R) E5-2682 CPUs at 2.50GHz

Datasets We generate large LDBC data sets with scale factor 30 using LDBC SNB Data Generator. The generated LDBC data sets which have 89 million vertices and 541 million edges would be used for the following experiments.

8thread, persistent storage, ms GAIA-X 70647 MG+v2 19299