Wed 10/2
Introduction Part 2 (slides)
The datacenter as a computer (BCH chapters 1, 2)
Mon 15/2
Introduction Part 2-continued (slides)
The datacenter as a computer (BCH chapters 1, 2)
Wed 24/2
Hardware architectures
A Reconfigurable Fabric for Accelerating Large-Scale Datacenter Services
Architecting to Achieve a Billion RPS Throughput on a Single Key-Value Store Server Platform
Presenters:
Mon 1/3
Energy & power
Heracles: improving resource efficiency at scale
Towards Energy Proportionality for Large-Scale Latency-Critical Workloads
Presenters:
Wed 3/3
No lecture
Mon 8/3
Datacenter storage
Pocket: Elastic Ephemeral Storage for Serverless Analytics
Presenters:
Wed 10/3
Winter break (No lecture)
Mon 15/3
Datacenter networking
Jupiter Rising: A Decade of Clos Topologies and Centralized Control in Google’s Datacenter Network
Azure Accelerated Networking: SmartNICs in the Public Cloud
Presenters:
Wed 17/3
Reliability (slides)
(Lecture notes, BCH chapter 7)
Mon 22/3
Application frameworks
Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing.
X-Stream: edge-centric graph processing using streaming partitions.
Presenters:
Wed 24/3
Serverless compute
Occupy the Cloud: Distributed Computing for the 99%
ExCamera -- Encoding, Fast and Slow: Low-Latency Video Processing Using Thousands of Tiny Threads
Presenters:
Mon 29/3
Microservices
Presenters:
Wed 31/3
Midterm (in class)
Mon 5/4
Performance Analysis
Profiling a Warehouse-Scale Computer
CPI2: CPU performance isolation for shared compute clusters
Presenters:
Wed 7/4
Tail latency
IX: a protected dataplane operating system for high throughput and low latency
Presenters:
Mon 12/4
Security
CryptDB: Protecting Confidentiality with Encrypted Query Processing
Shielding applications from an untrusted cloud with Haven
Presenters:
Wed 14/4
Privacy
Hey, You, Get Off of My Cloud: Exploring Information Leakage in Third-Party Compute Clouds
HomeAlone: Co-residency Detection in the Cloud via Side-Channel Analysis
Presenters:
Mon 19/4
Monitoring
Dapper, a Large-Scale Distributed Systems Tracing Infrastructure
The Mystery Machine: End-to-end Performance Analysis of Large-scale Internet Services
Presenters:
Wed 21/4
Datacenter management (slides)
(Lecture notes)
Mon 26/4
Spring Break (no lecture)
Wed 28/4
Cluster scheduling
Sparrow: distributed, low latency scheduling
Shinjuku: Preemptive Scheduling for μsecond-scale Tail Latency
Presenters:
Mon 3/5
ML in Systems
Quasar: Resource-Efficient and QoS-Aware Cluster Management
Presenters:
Wed 5/5
Cluster management
Large-scale cluster management at Google with Borg
Omega: Flexible, scalable schedulers for large compute clusters
Presenters:
Mon 10/5
Project presentations
Wed 12/5
Project presentations
Note: Paper presentations can be found in this folder.