Smoothing non-uniform communication latencies for OLTP
Summary: Analyzes 'Islands'—non-uniform core-to-core latencies—and shows workload partitionability and skew determine whether shared-nothing, shared-everything, or island-sized deployments win. Proposes ATraPos, a locality-aware shared-everything engine that auto-partitions state and pins workers to eliminate inter-socket accesses with lightweight monitoring and fast repartitioning. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 1 of 1 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 2,445 | OLTP on Hardware Islands | 2012 | VLDB | 8.8057827e-05 |
Previous
Page 1 / 1
Next