Monarch: Gaining Command on Geo-Distributed Graph Analytics

Transcript

1. Monarch: Gaining Command on Geo-Distributed Graph Analytics Anand Iyer ⋆, Aurojit Panda ▪, Mosharaf Chowdhury▴, Aditya Akella⬩, Scott Shenker ⋆, Ion Stoica ⋆ ⋆ UC Berkeley ▪ NYU ⬩ University of Wisconsin ▴ University of Michigan HotCloud, July 09, 2018
2. Graph Analytics Popular
3. Graph Analytics Popular Assume graph is aggregated to a single DC
4. Social Networks
5. Cellular Network Analytics
6. Financial Network Analytics Image courtesy: Neo4J
8. Generate data in a geo-distributed fashion
9. Can benefit from timely analysis Generate data in a geo-distributed fashion
10. How do we perform efficient geo-distributed graph analytics?
11. Apply query on samples of the input data Geo-Distributed Analytics (GDA) Slide courtesy: Clarinet authors
12. Apply query on samples of the input data Geo-Distributed Analytics (GDA) Clarinet [OSDI ‘16] Slide courtesy: Clarinet authors
13. Can we use the same idea on graphs? § GDA focuses on simple task placement/queries § Graph analytics iterative in nature § Flexibility over data placement and join sites § Graph partitioning difficult § Estimating intermediate data § Difficult in graph algorithms Geo-Distributed Analytics on Graphs
14. Can we use the same idea on graphs? § GDA focuses on simple task placement/queries § Graph analytics iterative in nature § Flexibility over data placement and join sites § Graph partitioning difficult § Estimating intermediate data § Difficult in graph algorithms Geo-Distributed Analytics on Graphs Key: Optimizing iterative graph-parallel processing
15. Graph Parallel Processing
16. Graph Parallel Processing Gather: Accumulate information from neighborhood
17. Graph Parallel Processing Gather: Accumulate information from neighborhood Apply: Apply the accumulated value
18. Graph Parallel Processing Gather: Accumulate information from neighborhood Apply: Apply the accumulated value Scatter: Update adjacent edges & vertices with new value
19. Our Proposal: Monarch DC 1 DC 3 DC 2 DC 4
20. Our Proposal: Monarch DC 1 DC 3 DC 2 DC 4 Sparsification
21. Our Proposal: Monarch DC 1 DC 3 DC 2 DC 4 Sparsification Execution Model
22. Our Proposal: Monarch DC 1 DC 3 DC 2 DC 4 Sparsification Execution Model WAN Awareness
23. Graph Sparsification § Sparsification extensively studied in graph theory § Idea: approximate the graph using a sparse, much smaller graph § Drop edges/vertices § Sparsify without accuracy loss § Only worry about reducing cross-DC entities § Leverage graph-parallel model and algorithm properties 0 1 4 2 3 0 1 4 2 3 DC1 DC2
24. Graph Sparsification § Sparsification extensively studied in graph theory § Idea: approximate the graph using a sparse, much smaller graph § Drop edges/vertices § Sparsify without accuracy loss § Only worry about reducing cross-DC entities § Leverage graph-parallel model and algorithm properties 0 1 4 2 3 0 1 4 2 3 DC1 DC2
25. Geo-Distributed Graph Computation Model DC 1 DC 3 DC 2 DC 4
26. Geo-Distributed Graph Computation Model DC 1 DC 3 DC 2 DC 4 Bootstrap
27. Geo-Distributed Graph Computation Model DC 1 DC 3 DC 2 DC 4 Bootstrap
28. Geo-Distributed Graph Computation Model DC 1 DC 3 DC 2 DC 4 Bootstrap Global Sync
29. Geo-Distributed Graph Computation Model DC 1 DC 3 DC 2 DC 4 Bootstrap Global Sync
30. Geo-Distributed Graph Computation Model DC 1 DC 3 DC 2 DC 4 Bootstrap Global Sync iGAS
31. Geo-Distributed Graph Computation Model DC 1 DC 3 DC 2 DC 4 Bootstrap Global Sync iGAS
32. Incremental GAS Model D C E F B A
33. Incremental GAS Model D C E F B A
34. Incremental GAS Model D C E F B A
35. Incremental GAS Model D C E F B A
36. Incremental GAS Model D C E F B A
37. Incremental GAS Model D C E F B A
38. Incremental GAS Model D C E F B A
39. Incremental GAS Model D C E F B A
40. Incremental GAS Model D C E F B A Which graph algorithms can use the iGAS model? How much state needs to be kept at the entities for accuracy?
41. Geo-Distributed Graph Computation Model DC 1 DC 3 DC 2 DC 4 Bootstrap Global Sync iGAS
42. Geo-Distributed Graph Computation Model DC 1 DC 3 DC 2 DC 4 Bootstrap Global Sync iGAS
43. Geo-Distributed Graph Computation Model DC 1 DC 3 DC 2 DC 4 Bootstrap Global Sync iGAS
44. Geo-Distributed Graph Computation Model DC 1 DC 3 DC 2 DC 4 Bootstrap Global Sync iGAS Apply GDA techniques on task placement and data movement
45. Evaluation of Potential § 16 node Apache Spark cluster across 4 regions § Modified GraphX to incorporate the proposed model � ��� ��� ��� ��� ��� ������ ������� � ���� ���� ���� ���� ����� ����� ����� ��������� ���� ��� ���� ����������� ���� ��������� ���� ��� ���� ���������� 0 100 200 300 400 500 4 regions 2 regions 0 2000 4000 6000 8000 10000 12000 14000 Execution Time (s) Data Transferred (MB) Execution Time Data Transfered
46. Other Open Questions § Convergence properties due to our modified execution model § Better execution models at bootstrap stage § How would the global sync work? § Multi-tenancy § Would it provide opportunities to leverage existing GDA techniques? § Graph updates § What is an incremental model in this case?
47. Conclusion § Several emerging applications produce graph data in a geo-distributed fashion § Can benefit from geo-distributed graph analytics. § Our proposal Monarch: § Early attempt at bringing geo-distributed analytics to graph processing. § Initial results are encouraging. http://www.cs.berkeley.edu/~api api@cs.berkeley.edu