About me: I am a Computer Science Ph.D. student at UC Santa Barbara's Distributed Systems Lab (DSL). I work in the intersection of data management and distributed systems to advance the area of Global-Scale Data Management. Also, I have worked in collaboration with HP Labs and Microsoft Research to build data management designs on emerging memory hardware technology.
My C.V. can be found here
Research Statement: Data is generated and consumed throughout the world. Processing this data is essential to drive todays Internet Services and Big Data Analytics. In my work, I study and build data management systems for global-scale environments with the goal of understanding the fundamental challenges and design practices to support such an environment.
Looking forward, the demand for global-scale data management will surpass those of current human-driven Internet Services and Big Data Analytics with the emergence of autonomous applications such as Internet of Things (IoT), mobile agents (self-driving cars and robotics), and data-driven sciences ranging from the social sciences to medicine. My ongoing work explores the opportunities and challenges in augmenting edge computing technology and application-level research with data management capabilities that support the next 10x and 100x explosion in globally connected devices and data.
Click here for more about my work on global-scale data management
Projects and publications
Processing Geo-Replicated Data: This line of work studies and design transaction processing protocols for geo-replicated data. The large latency between datacenters is a challenge to performance. This invites designing new protocols that target geo-replication.
COP: Planning Conflicts for Faster Parallel Transactional Machine Learning
Low-Latency Multi-Datacenter Databases using Replicated Commits.
Managing Geo-replicated Data in Multi-datacenters.
(Springer Databases in Networked Information Systems 2013)
Speed-of-Light Limit on Coordination Latency: Transaction latency on geo-replicated data is limited by the speed-of-light. A theoretical lower-bound of transaction latency is developed to understand the limits imposed by large communication latency. Using insights from the lower-bound, a protocol called Helios is developed that theoretically achieves the lower-bound and approach it in real experiments
Data processing on emerging memory technology: In collaboration with HP Labs, I worked on designing data stores for non-volatile memory architectures. I studied the implications of emerging flush-on-fail CPU technology on the durability cost of transactions. Also, as an intern in MSR Redmond I worked on the Time-Split Bw-tree (TSBw-tree) that integrates the algorithms of the Time-split B-tree within the lock-free implementation of the Bwtree.
Fair resource allocation for Wireless Mesh Networks: This project tackles the problem of unfairness in Wireless Mesh Networks, where TCP flows experience different performance characteristics depending on their location in the network. A MAC-layer solution is developed to transparently improve TCP fairness. The proposed MAC layer, called TMAC, uses a timestamp-ordering technique to achieve fairness.
Fair Packet Scheduling in Wireless Mesh Networks.
(Elsevier Journal of Ad Hoc Networks 2014)
MAC-Layer Protocol for TCP Fairness in Wireless Mesh Networks.
TMAC: Timestamp-ordered MAC for CSMA/CA Wireless Mesh Networks.
TMAC: Timestamp-Ordered MAC Protocol for Wireless Mesh Networks.
(MS Thesis 2011)
Other work on large-scale data processing