Running Neo4j in Production: Tips, Tricks and Optimizations
Download as PPTX, PDF0 likes537 views
This document summarizes tips for running Neo4j in production from a talk given by David Fox from SNAP Interactive, a social dating app. Some key points include: using Java batch inserters and sorting to import billions of nodes and relationships efficiently; testing Cypher CSV import; benchmarking and caching queries; distributing writes with Baserunner; tuning the garbage collector; using SSDs for large working sets; and looking forward to new features in upcoming Neo4j versions. The talk provided lessons learned from scaling SNAP's graph to support millions of users on their dating application.
Running Neo4j in Production: Tips, Tricks and Optimizations
- 1. Running Neo4j in Production Tips, Tricks and Optimizations
- 2. This Talk... ● How we scaled our prod graph ● Challenges faced doing this ● Various lessons we learned and techniques we used ● Some stuff I’m looking forward to in Neo4j
- 3. SNAP Interactive ● Presented by David Fox (Big Data Engineer) ● Social dating app AYI (Are You Interested?) ● Friends and interests
- 4. How We Use Neo4j ● Model the friend data of our millions of users ● Indicate connections everywhere on app ● 1.1+ billion nodes ● 8.5+ billion relationships ● 450gb+ store ● 3 instance cluster
- 5. Importing lots of data ● Find the right tool o First try normal Cypher o No good? Bring out the big guns - Java Batch Inserter ● Java Batch Inserter o Sort relationships (GNU sort) o Try to keep index lookups to in-memory lookups only Giant HashMap!
- 6. But wait!!! ● Cypher CSV import o 2.1 M01 o Supposed to be good for importing large data sets o Anyone tried it?
- 7. Read Querying ● Always try Cypher first o Performance is being improved ● How can you tell if performance is where you need it to be? o Time queries (cold vs. warm cache) o Load testing!
- 8. Read Querying cont. ● Dark querying o Great for benchmarking system where Neo4j functionality is being injected o Mitigates risk o Provides results that are very close to real world patterns
- 9. Read Querying cont. ● Reads too slow? Try these things. o Write high-throughput business-critical queries in Java unmanaged extension faster hard limits o Cache shard country, age, gender, etc. you hit warm cache more often
- 10. Read Querying cont. ● Warm the cache! o Touch all the nodes o Touch all the relationships
- 11. Writing ● Decide which writes need to be synchronous and which can be asynchronous ● Queue up asynchronous writes (routine updates, non-vital to immediate user- experience) o Try to evenly distribute them o How do we do this? Baserunner!
- 12. Baserunner ● Written by SNAP developer ● Walks userbase randomly instead of sequentially o This avoids pockets of heavily increased write queries o Allows us to do high-velocity updating of our data
- 13. Tuning the JVM ● For a really high-throughput environment, G1 GC has been very helpful o Good at adapting itself o We experienced less system-stopping pauses than with CMS o Try CMS first but remember G1 as option
- 14. Hardware is Important ● Lots of memory ● Working set too big for memory? o SSDs are helpful o Optimization techniques discussed become much more important
- 15. Not Everything is Your Fault! ● Like any software, Neo4j has bugs ● Developers are receptive ● File reports on Github when you find issues
- 16. Some stuff to look forward to... ● Relationship grouping (2.1 M01) o helps mitigate the super node/dense node problem ● Ronja (rewrite of the Cypher query language, 2.1?) ● More flexible label index searching (after 2.1)
- 17. Questions?