Cloud-Native Database with Storage Disaggregation


Xiangyao Yu
University of Wisconsin - Madison


Sam Madden
Cloud-Native Database with Storage Disaggregation
Modern databases are moving to the cloud for high elasticity and flexible pricing model (e.g., pay-as-you-go). Cloud-native databases adopt a unique storage-disaggregation architecture, where the computation and storage are decoupled as two separate services connected through the data center network. The new storage-disaggregation architecture demands a revisit of database system design. In this talk, I will discuss our research in optimized disaggregated database systems in both transactional and analytical workloads. In particular, I will present Cornus, an optimized two-phase commit (2PC) protocol that leverages highly-available storage services to reduce latency and enhance reliability for distributed transactions. I will also discuss our recent work on computation pushdown, where the database leverages storage-layer computation (i.e., a pushdown layer) to accelerate data analytics processing. I will conclude the talk with our on-going research and future plans on cloud-native database systems.
Short Bio
Xiangyao Yu is an Assistant Professor at the University of Wisconsin-Madison. His research interests include (1) cloud-native databases, (2) new hardware for databases, and (3) transactions and HTAP. Before joining UW-Madison, he finished postdoc and PhD at MIT and bachelor at Tsinghua University.

Zoom option:
Tianyu Li is inviting you to a scheduled Zoom meeting.

Join Zoom Meeting

Password: 329527

One tap mobile
+16465588656,,92698683855# US (New York)
+16699006833,,92698683855# US (San Jose)

Meeting ID: 926 9868 3855

US : +1 646 558 8656 or +1 669 900 6833

International Numbers:

Join by SIP

Join by Skype for Business