Rui's Blog
  • Rui's Blog/Paper Reading Notes - Introduction
  • Personal Blog
    • Personal Blog - Index
      • How to Create Picture-in-Picture Effect / Video Overlay for a Presentation Video
      • How to Do Your Part to Protect the Environment in Wisconsin
      • How to Get a Driver's License in Wisconsin
      • How to Travel from the U.S. to China onboard AA127 in June 2021
      • How to Transfer Credits Back to UW-Madison
      • Resources on Learning Academic Writing (for Computer Science)
    • Towards applying to CS Ph.D. programs
  • Machine Learning Systems
    • Machine Learning Systems - Index
      • MLSys Papers - Short Notes
      • [2011 NSDI] Dominant Resource Fairness: Fair Allocation of Multiple Resource Types
      • [2014 OSDI] Scaling Distributed Machine Learning with the Parameter Server
      • [2018 OSDI] Gandiva: Introspective Cluster Scheduling for Deep Learning
      • [2018 SIGCOMM] Chameleon: Scalable Adaptation of Video Analytics via Temporal and Cross-camera ...
      • [2018 NIPS] Dynamic Space-Time Scheduling for GPU Inference
      • [2019 ATC] Analysis of Large-Scale Multi-Tenant GPU Clusters for DNN Training Workloads
      • [2019 NSDI] Tiresias: A GPU Cluster Manager for Distributed Deep Learning
      • [2019 SOSP] ByteScheduler: A Generic Communication Scheduler for Distributed DNN Training ...
      • [2019 SOSP] PipeDream: Generalized Pipeline Parallelism for DNN Training
      • [2019 SOSP] Parity Models: Erasure-Coded Resilience for Prediction Serving Systems
      • [2019 NIPS] GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism
      • [2019 SC] ZeRO: memory optimizations toward training trillion parameter models
      • [2020 OSDI] Gavel: Heterogeneity-Aware Cluster Scheduling Policies for Deep Learning Workloads
      • [2020 OSDI] AntMan: Dynamic Scaling on GPU Clusters for Deep Learning
      • [2020 OSDI] BytePS: A High Performance and Generic Framework for Distributed DNN Training
      • [2020 SIGCOMM] Reducto: On-Camera Filtering for Resource-Efficient Real-Time Video Analytics
        • [2020 MLSys] Salus: Fine-Grained GPU Sharing Primitives for Deep Learning Applications
      • [2020 EuroSys] AlloX: Compute Allocation in Hybrid Clusters
      • [2020 VLDB] PyTorch Distributed: Experiences on Accelerating Data Parallel Training
      • [2020 NetAI] Is Network the Bottleneck of Distributed Training?
      • [2020 NSDI] Themis: Fair and Efficient GPU Cluster Scheduling
      • [2021 MLSys] Accordion: Adaptive Gradient Communication via Critical Learning Regime Identification
      • [2021 VLDB] Analyzing and Mitigating Data Stalls in DNN Training
      • [2021 FAST] CheckFreq: Frequent, Fine-Grained DNN Checkpointing
      • [2021 EuroMLSys] Interference-Aware Scheduling for Inference Serving
      • [2021 OSDI] Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning
      • [2021 MLSys] Wavelet: Efficient DNN Training with Tick-Tock Scheduling
      • [2021 NSDI] SwitchML: Scaling Distributed Machine Learning with In-Network Aggregation
    • Big Data Systems - Index
      • Big Data Systems Papers - Short Notes
      • [2003 SOSP] The Google File System
      • [2004 OSDI] MapReduce: Simplified Data Processing on Large Clusters
      • [2010 SIGMOD] Pregel: A System for Large-Scale Graph Processing
      • [2011 NSDI] Mesos: A Platform for Fine-Grained Resource Sharing in the Data Center
      • [2012 NSDI] Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster ...
      • [2012 OSDI] PowerGraph: Distributed Graph-Parallel Computation on Natural Graphs
      • [2019 FAST] DistCache: Provable Load Balancing for Large-Scale Storage Systems with Distributed...
      • [2021 HotOS] From Cloud Computing to Sky Computing
      • [2021 EuroSys] NextDoor: Accelerating graph sampling for graph machine learning using GPUs
  • Earlier Readings & Notes
    • High Performance Computing Course Notes
      • Lecture 1: Course Overview
      • Lecture 2: From Code to Instructions. The FDX Cycle. Instruction Level Parallelism.
      • Lecture 3: Superscalar architectures. Measuring Computer Performance. Memory Aspects.
      • Lecture 4: The memory hierarchy. Caches.
      • Lecture 5: Caches, wrap up. Virtual Memory.
      • Lecture 6: The Walls to Sequential Computing. Moore’s Law.
      • Lecture 7: Parallel Computing. Flynn's Taxonomy. Amdahl's Law.
      • Lecture 8: GPU Computing Intro. The CUDA Programming Model. CUDA Execution Configuration.
      • Lecture 9: GPU Memory Spaces
      • Lecture 10: GPU Scheduling Issues.
      • Lecture 11: Execution Divergence. Control Flow in CUDA. CUDA Shared Memory Issues.
      • Lecture 12: Global Memory Access Patterns and Implications.
      • Lecture 13: Atomic operations in CUDA. GPU ode optimization rules of thumb.
      • Lecture 14: CUDA Case Studies. (1) 1D Stencil Operation. (2) Vector Reduction in CUDA.
      • Lecture 15: CUDA Case Studies. (3) Parallel Prefix Scan on the GPU. Using Multiple Streams in CUDA.
      • Lecture 16: Streams, and overlapping data copy with execution.
      • Lecture 17: GPU Computing: Advanced Features.
      • Lecture 18: GPU Computing with thrust and cub.
      • Lecture 19: Hardware aspects relevant in multi-core, shared memory parallel computing.
      • Lecture 20: Multi-core Parallel Computing with OpenMP. Parallel Regions.
      • Lecture 21: OpenMP Work Sharing.
      • Lecture 22: OpenMP Work Sharing
      • Lecture 23: OpenMP NUMA Aspects. Caching and OpenMP.
      • Lecture 24: Critical Thinking. Code Optimization Aspects.
      • Lecture 25: Computing with Supercomputers.
      • Lecture 26: MPI Parallel Programming General Introduction. Point-to-Point Communication.
      • Lecture 27: MPI Parallel Programming Point-to-Point communication: Blocking vs. Non-blocking sends.
      • Lecture 28: MPI Parallel Programming: MPI Collectives. Overview of topics covered in the class.
    • Cloud Computing Course Notes
      • 1.1 Introduction to Clouds, MapReduce
      • 1.2 Gossip, Membership, and Grids
      • 1.3 P2P Systems
      • 1.4 Key-Value Stores, Time, and Ordering
      • 1.5 Classical Distributed Algorithms
      • 4.1 Spark, Hortonworks, HDFS, CAP
      • 4.2 Large Scale Data Storage
    • Operating Systems Papers - Index
      • CS 736 @ UW-Madison Fall 2020 Reading List
      • All File Systems Are Not Created Equal: On the Complexity of Crafting Crash-Consistent Applications
      • ARC: A Self-Tuning, Low Overhead Replacement Cache
      • A File is Not a File: Understanding the I/O Behavior of Apple Desktop Applications
      • Biscuit: The benefits and costs of writing a POSIX kernel in a high-level language
      • Data Domain: Avoiding the Disk Bottleneck in the Data Domain Deduplication File System
      • Disco: Running Commodity Operating Systems on Scalable Multiprocessors
      • FFS: A Fast File System for UNIX
      • From WiscKey to Bourbon: A Learned Index for Log-Structured Merge Trees
      • LegoOS: A Disseminated, Distributed OS for Hardware Resource Disaggregation
      • LFS: The Design and Implementation of a Log-Structured File System
      • Lottery Scheduling: Flexible Proportional-Share Resource Management
      • Memory Resource Management in VMware ESX Server
      • Monotasks: Architecting for Performance Clarity in Data Analytics Frameworks
      • NFS: Sun's Network File System
      • OptFS: Optimistic Crash Consistency
      • RAID: A Case for Redundant Arrays of Inexpensive Disks
      • RDP: Row-Diagonal Parity for Double Disk Failure Correction
      • Resource Containers: A New Facility for Resource Management in Server Systems
      • ReVirt: Enabling Intrusion Analysis through Virtual-Machine Logging and Replay
      • Scheduler Activations: Effective Kernel Support for the User-Level Management of Parallelism
      • SnapMirror: File-System-Based Asynchronous Mirroring for Disaster Recovery
      • The Linux Scheduler: a Decade of Wasted Cores
      • The Unwritten Contract of Solid State Drives
      • Venti: A New Approach to Archival Storage
    • Earlier Notes
      • How to read a paper
  • FIXME
    • Template for Paper Reading Notes
Powered by GitBook
On this page
  • One-line Summary
  • Paper Structure Outline
  • Background & Motivation
  • Design and Implementation
  • Evaluation
  • New Vocabulary
  • Links

Was this helpful?

  1. Earlier Readings & Notes
  2. Operating Systems Papers - Index

Resource Containers: A New Facility for Resource Management in Server Systems

One-line Summary

A resource container is an operating systems abstraction that separates the notion of a protection domain from a resource principal. It allows for fine-grained resource management.

Paper Structure Outline

  1. Introduction

  2. Typical models for high-performance servers

  3. Shortcomings of current resource management models

    1. The distinction between scheduling entities and activities

    2. Integrating network processing with resource management

    3. Consequences of misidentified resource principals

  4. A new model for resource management

    1. Resource containers

    2. Containers, processes, and threads

    3. Resource containers and CPU scheduling

    4. Other resources

    5. The resource container hierarchy

    6. Operations on resource containers

    7. Kernel execution model

    8. The use of resource containers

  5. Performance

    1. Prototype implementation

    2. Experimental environment

    3. Baseline throughput

    4. Costs of new primitives

    5. Prioritized handling of clients

    6. Controlling resource usage of CGI processing

    7. Immunity against SYN-flooding

    8. Isolation of virtual servers

  6. Related Work

  7. Conclusion

Background & Motivation

In resource management, current systems do not separate the notion of "protection domain" (where the accounting of the tasks is done) and "resource principal" (where actual work gets performed). Processes and threads are both resource principals as well as protection domains. Also, an application does not have control over how much resources the kernel consumes on behalf of the application. In this work, the two notions are separated by the new operating systems abstraction, resource containers.

Existing models include (1) process-per connection, (2) single-process event-driven connection, and (3) multi-threaded server.

The authors then presented some analyses in section 3 to analyze the shortcomings of the current models.

Design and Implementation

Instead of binding threads of application space processes, threads bind to different resource containers (RC), a new abstraction that extends into the kernel and thus has knowledge of which os entities are doing work for which application-level clients. Resource containers logically contain all types of resources (CPU time, sockets, control blocks, network buffers) being used by an application. Containers are also attached with attributes to limit resources (CPU availability), provide scheduling priorities, and network QoS values.

To use resource containers with multiple threads:

  • Threads are assigned to RCs for each new connection as soon as identified from request info

  • Kernel processing is charged to this container

  • We can have different RCs for different QoS policies

  • The OS scheduler appropriately schedules threads by priority/resource usage. If the thread consumes more than its fair share of resources, its scheduling priority decays.

To use resource containers with events:

  • Threads switch to the desired resource containers as they handle new events

  • No need for scheduling by OS

  • The associated container will be charged for the processing the thread performs for them

  • Resource containers just track accounting

  • Applications use the information to determine the order to handle events

Evaluation

Resource containers allow explicit and fine-grained control over resource consumption at both user-level and kernel-level. They can provide accurate resource accounting, enabling web servers to provide differentiated QoS.

New Vocabulary

  • Resource principals: Entities for which separate resource allocation and accounting are done

  • Protection domain: Entities that need to be isolated from each other

  • QoS: Quality of Service

Links

PreviousRDP: Row-Diagonal Parity for Double Disk Failure CorrectionNextReVirt: Enabling Intrusion Analysis through Virtual-Machine Logging and Replay

Last updated 4 years ago

Was this helpful?

Paper PDF
Lecture slides from EECS 443 @ Northwestern University
Lecture slides from CS 5204 @ Virginia Polytechnic
Discussion panel from CS 736 @ UW-Madison
743KB
17-resourcecontainers.pptx
CS 736 course slides on resource containers by Prof. Andrea Arpaci-Dusseau
Restricting resource usage of dynamic requests allows the OS to deliver a certain degree of fairness across containers
RCs are effective in the prioritized handling of clients (have better response time) as they prevent work in the kernel
Resource utilization can be controlled by isolating static requests being serviced
Containers help provide a certain amount of immunity against a DOS attack by SYN flooding.