Pinchao Liu

Pinchao Liu

Auto-generated profile, based on publicly available information

Pinchao Liu

School of Computing and information Science, Florida International University, Miami, FL, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 March 2023 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
HXHailu Xu
Hailu Xu
PLPinchao Liu
Pinchao Liu
SASarker Tanzir Ahmed
Sarker Tanzir Ahmed
DSDilma Da Silva
Dilma Da Silva
LHLiting Hu
Liting Hu
Today, large-scale cloud organizations are deploying datacenters and “edge” clusters globally to provide low-latency access to services. Running stream applications across geo-distributed sites are emerging as a daily requirement. However, existing efforts have dominantly centered around stateless stream processing , leaving another urgent trend- stateful stream processing -much less explored. A driving need is to store and update states during processing, and most importantly, successfully recover large distributed states when faults and failures happen. Existing studies exhibit major limitations including: (1) they mostly inherit MapReduce's “single master/many workers” architecture, where the central master can easily become ascalability bottleneck; (2) they offer state recovery mainly through three approaches: replication recovery, checkpointing recovery, and DStream-based lineage recovery, which are either slow, resource-expensive or failing to handle multiple failures; and (3) they are not adaptive to heterogeneous hardware settings. We present A-FP4S, a novel adaptive fragments-based parallel state recovery mechanism for stream processing systems. A-FP4S organizes stream operators into a distributed hash table based peer-to-peer overlay and divides each node's local state into many fragments. These fragments are periodically stored in node's multiple neighbors, ensuring different sets of available fragments can reconstruct failed states in parallel. This mechanism is extremely scalable to the lost state, significantly reduces failure recovery time, and can tolerate multiple node failures. A-FP4S is adaptive to heterogeneous hardware settings by automatic parameter tuning over phases. Compared to Apache Storm, A-FP4S achieves 31.8% to 50.5% reduction in recovery latency. Large-scale experiments using real-world datasets demonstrate A-FP4S's attractive scalability and adaptivity properties.

9 January 2023
Verified
Thesis
Open access
PDF file
PLPinchao Liu
Pinchao Liu
The past few years have seen dramatic growth in the popularity of public clouds, such as Infrastructure-as-a-Service (IaaS), Platform-as-a-Service (PaaS), and Container-as-a-Service (CaaS). In both commercial and scientific fields, quick environment setup and application deployment become a mandatory requirement. As a result, more and more organizations choose cloud environments instead of setting up the environment by themselves from scratch. The cloud computing resources such as server engines, orchestration, and the underlying server resources are served to the users as a service from a cloud provider. Most of the applications that run in public clouds are the distributed applications, also called multi-tier applications, which require a set of servers, a service ensemble, that cooperate and communicate to jointly provide a certain service or accomplish a task. Moreover, a few research efforts are conducting in providing an overall solution for distributed applications optimization in the public cloud. In this dissertation, we present three systems that enable distributed applications optimization: (1) the first part introduces DocMan, a toolset for detecting containerized application’s dependencies in CaaS clouds, (2) the second part introduces a system to deal with hot/cold blocks in distributed applications, (3) the third part introduces a system named FP4S, a novel fragment-based parallel state recovery mechanism that can handle many simultaneous failures for a large number of concurrently running stream applications.