Database Paper Browser

Back to papers

Magnet: Push-based Shuffle Service for Large-scale Data Processing

Summary: Magnet introduces a push-based shuffle service that merges fragmented intermediate data into large blocks, co-locating with reduce tasks. Scales to petabytes on thousands of nodes, on-prem and cloud, delivering ~30% speedups and reducing tuning burden. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID
12217
Venue
VLDB
Year
2020
Pagerank
5.2873617e-05
Overall Rank
5,888 | 59.04%
DOI
10.14778/3415478.3415558

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 5 of 5 citing papers.

Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 3 of 3 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank Cited Paper Year Venue Pagerank
66 Spark SQL: Relational Data Processing in Spark 2015 SIGMOD 0.00061639801
1,071 Starfish: A Self-tuning System for Big Data Analytics 2011 CIDR 0.00014312777
4,248 Hyper Dimension Shuffle: Efficient Data Repartition at Petabyte Scale in SCOPE 2019 VLDB 6.3247927e-05
Previous Page 1 / 1 Next

Semantically Similar Papers