seminar

Seminar

Time: Every Tuesday 14:00

Place: Room 3201, School of Software

Autumn 2021

Selected Papers

• Themis: Fair and Efficient GPU Cluster Scheduling, NSDI ‘20
• Blending Containers and Virtual Machines: A Study of Firecracker and gVisor, VEE ‘20
• Heterogeneity-Aware Cluster Scheduling Policies for Deep Learning Workloads, OSDI ‘20
• Evolution of Development Priorities in Key-value Stores Serving Large-scale Applications: The RocksDB Experience, FAST ‘21
• Differentiated Key-Value Storage Management for Balanced I/O Performance, USENIX ATC ‘21
• Consistency and Completeness: Rethinking Distributed Stream Processing in Apache Kafka, SIGMOD ‘21
• RAS: Continuously Optimized RegionWide Datacenter Resource Allocation, SOSP ’21
• Kangaroo: Caching Billions of Tiny Objects on Flash, SOSP ’21
• Good Things Come to Those Who Wait: Optimizing Job Waiting in the Cloud, SoCC ‘21
• Atoll: A Scalable Low-Latency Serverless Platform, SoCC ‘21
• Ownership: A Distributed Futures System for Fine-Grained Tasks, NSDI ‘21
• Ship Compute or Ship Data? Why Not Both?, NSDI ‘21
• Automatically Detecting and Fixing Concurrency Bugs in Go Software Systems, ASPLOS ‘21
• Unikraft: Fast, Specialized Unikernels the Easy Way, EuroSys ‘21
• Tell me when you are sleepy and what may wake you up!, SoCC ‘21
• Mu: An Efficient, Fair and Responsive Serverless Framework for Resource-Constrained Edge Clouds, SoCC ‘21
• SHOWAR: Right-Sizing And Efficient Scheduling of Microservices, SoCC ‘21
• Mind the Gap: Broken Promises of CPU Reservations in Containerized Multi-tenant Clouds, SoCC ‘21
• PaSh: Light-touch Data-Parallel Shell Processing, EuroSys ‘21

Date	Topic	Speaker	Papers
2021-11-09	Time Series Database	Hongyi Long	Gorilla: A Fast, Scalable, In-Memory Time Series Database [VLDB ‘15]
2021-11-23	Resource Management	Sho Itami	RAS: Continuously Optimized RegionWide Datacenter Resource Allocation [SOSP ‘21]
2021-11-30	Storage	Zhao Jiang	Evolution of Development Priorities in Key-value Stores Serving Large-scale Applications: The RocksDB Experience [FAST ‘21]
2021-12-07	Scheduling	Haoyu Wang	Mind the Gap: Broken Promises of CPU Reservations in Containerized Multi-tenant Clouds [SoCC ‘21]
2021-12-14	Resource Management	Chao Li	Providing SLOs for Resource-Harvesting VMs in Cloud Platforms [OSDI ‘20]
2021-12-21	Serverless	Yalun Lin Hsu
2021-12-28	Resource Management	Yan Yu	SmartHarvest: Harvesting Idle CPUs Safely and Efficiently in the Cloud [EuroSys ‘21]
2021-12-28	Cache	Jie Lian	Segcache: a memory-efficient and scalable in-memory key-value cache for small objects [NSDI ‘21]

Spring 2021

Date	Topic	Speaker	Papers
2021-03-03	Microservice	Xiaoran Wang	FIRM: An Intelligent Fine-grained Resource Management Framework for SLO-Oriented Microservices [OSDI '20]
2021-03-10	Storage	Zhiyuan Wang	Amazon Aurora: Design Considerations for High Throughput Cloud-Native Relational Databases [SIGMOD '17]
2021-04-07	Resource Management	Haoyuan Hu	Twine: A Unified Cluster Management System for Shared Infrastructure [OSDI '20]
2021-04-14	Data Warehouse	Yufan Jiang	The Snowflake Elastic Data Warehouse [SIGMOD '16]
2021-04-21	Storage	Yang Zhao	Ceph: A Scalable, High-Performance Distributed File System [OSDI '06]
2021-04-28	Distributed System	Jinke Liu	MilliSort and MilliQuery: Large-Scale Data-Intensive Computing in Milliseconds [NSDI '21]

Autumn 2020

Date	Topic	Speaker	Papers
2020-09-21	Resource Management	Yuchen Cheng	Large-scale cluster management at Google with Borg [EuroSys '15] Autopilot: workload autoscaling at Google [EuroSys '20] Borg, Omega, and Kubernetes: Lessons learned from three container-management systems over a decade (Optional)
		Yalun Lin Hsu	Medea: scheduling of long running applications in shared production clusters [EuroSys '18] Neptune: Scheduling Suspendable Tasks for Unified Stream/Batch Applications [SoCC '19]
2020-09-28	Serverless	Yalun Lin Hsu	Cloud Programming Simplified: A Berkeley View on Serverless Computing SOCK: Rapid Task Provisioning with Serverless-Optimized Containers [USENIX ATC '18]
		Yuchen Cheng	SAND: Towards High-Performance Serverless Computing [USENIX ATC '18] Serverless in the Wild: Characterizing and Optimizing the Serverless Workload at a Large Cloud Provider [USENIX ATC '20]
2020-10-09	Batch Processing	Hongyi Long	Resilient distributed datasets: a fault-tolerant abstraction for in-memory cluster computing [NSDI '12]
		Zhiyuan Ma	Riffle: optimized shuffle service for large-scale data analytics [EuroSys '18]
		Zhenglin Xu	Magnet: push-based shuffle service for large-scale data processing [VLDB '20]
2020-10-12	Stream Processing	Yalun Lin Hsu	The dataflow model: a practical approach to balancing correctness, latency, and cost in massive-scale, unbounded, out-of-order data processing [VLDB '15] Apache Flink™: Stream and Batch Processing in a Single Engine Lightweight Asynchronous Snapshots for Distributed Dataflows
		Yuchen Cheng	Drizzle: Fast and Adaptable Stream Processing at Scale [SOSP '17] Structured Streaming: A Declarative API for Real-Time Applications in Apache Spark [SIGMOD '18]
2020-10-19	Machine Learning Frameworks	Yuchen Cheng	Scaling Distributed Machine Learning with the Parameter Server [OSDI '14] TensorFlow: A System for Large-Scale Machine Learning [OSDI '16]
		Yalun Lin Hsu	Clipper: A Low-Latency Online Prediction Serving System [NSDI '17] [notes] Ray: A Distributed Framework for Emerging AI Applications [OSDI '18]
2020-10-26	Key-Value Stores (Log-Structured Merge-Tree)	Wanqiang Zhang	SuRF: Practical Range Query Filtering with Fast Succinct Tries [SIGMOD '18] Rosetta: A Robust Space-Time Optimized Range Filter for Key-Value Stores [SIGMOD '20]
	Stream Processing	Yuchen Cheng	Samza: stateful scalable stream processing at LinkedIn [VLDB '17]
		Yalun Lin Hsu	Turbine: Facebook’s Service Management Platform for Stream Processing [ICDE '20]
2020-11-02	Stream Processing	Yuchen Cheng	Prompt: Dynamic Data-Partitioning for Distributed Micro-batch Stream Processing Systems [SIGMOD '20]
		Yalun Lin Hsu	TerseCades: Efficient Data Compression in Stream Processing [USENIX ATC '18]
2020-11-16	Serverless	Yalun Lin Hsu	Cloudburst: stateful functions-as-a-service [VLDB '20]
2020-11-23	Stream Processing	Yuchen Cheng	Move Fast and Meet Deadlines: Fine-grained Real-time Stream Processing with Cameo [NSDI '21]
2020-11-30	Serverless	Yalun Lin Hsu	Optimizing Prediction Serving on Low-Latency Serverless Dataflow
2020-12-14	Serverless	Yalun Lin Hsu	Understanding Ephemeral Storage for Serverless Analytics [USENIX ATC '18] Pocket: Elastic Ephemeral Storage for Serverless Analytics [OSDI '18]

This site is open source. Improve this page.