DBScholar

Back to papers

Narwhal: Breaking the Local Boundary via Disaggregated Memory Scheduling for Alibaba AnalyticDB

Summary: Narwhal co-schedules local DRAM with an RDMA-disaggregated shared pool, breaking per-machine memory boundaries for bursty OLAP. Hardware-isolated quotas/QoS, a database-aware three-tier cache, and pressure invariants prevent OOMs while enabling high oversubscription with minimal remote borrowing. (summarized by gpt-5.6-luna on Aug 28 2026)

Paper ID
h88b3d0ae00aad7bb
Venue
VLDB
Year
2026
Pagerank
4.9793485e-05
Overall Rank
10,949 | 26.39%
DOI
10.14778/3827998.3828046

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

BibTeX Citation

@article{zhou_vldb26,
        title = {{Narwhal: Breaking the Local Boundary via Disaggregated Memory Scheduling for Alibaba AnalyticDB}},
        author = {Zhou, Jian and Zhang, Jiachi and Zhang, Yang and Wang, Yongbo and Guo, Ruonan and Wu, Yuemin and Chang, Zeguang and Wang, Shuai and Yin, Ye and Zhou, Wenchao and Lin, Liang},
        journal = {PVLDB},
        series = {{VLDB} '26},
        volume = {19},
        number = {12},
        pages = {4466--4479},
        doi = {10.14778/3827998.3828046},
        url = {https://doi.org/10.14778/3827998.3828046},
        year = {2026}
}

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 11 of 11 cited papers.

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

Previous Page 1 / 1 Next

Semantically Similar Papers