• Corpus ID: 52987224

LegoOS: A Disseminated, Distributed OS for Hardware Resource Disaggregation

@inproceedings{Shan2018LegoOSAD,
  title={LegoOS: A Disseminated, Distributed OS for Hardware Resource Disaggregation},
  author={Yizhou Shan and Yutong Huang and Yilun Chen and Yiying Zhang},
  booktitle={OSDI},
  year={2018}
}
The monolithic server model where a server is the unit of deployment, operation, and failure is meeting its limits in the face of several recent hardware and application trends. To improve resource utilization, elasticity, heterogeneity, and failure handling in datacenters, we believe that datacenters should break monolithic servers into disaggregated, network-attached hardware components. Despite the promising benefits of hardware resource disaggregation, no existing OSes or software systems… 

Figures from this paper

Network in Disaggregated Datacenters
TLDR
It is shown that networking can be disaggregated following the same principles, and that classical networking optimizations such as DMA, DDIO or loopback can be reproduced in such an environment.
Caladan: a distributed meta-OS for data center disaggregation
TLDR
Caladan is a novel system with a trusted universal resource fabric that interconnects all resources and efficiently offloads the system and application control planes to SmartNICs, freeing server CPUs to execute application logic.
PolarDB Serverless: A Cloud Native Database for Disaggregated Data Centers
TLDR
The novel architecture of \name is described, which follows the disaggregregation design paradigm: the CPU resource on compute nodes is decoupled from remote memory pool and storage pool, and each resource pool grows or shrinks independently.
Disaggregating Persistent Memory and Controlling Them Remotely: An Exploration of Passive Disaggregated Key-Value Stores
TLDR
This paper explores the design of disaggregating PM and managing them remotely from compute servers, a model the authors call passive disaggregated persistent memory, or pDPM, which significantly lowers monetary and energy costs and avoids scalability bottlenecks at storage servers.
1 Co-Designing State Machine Replication with the Datacenter Network : Speculative Paxos and NOPaxos
TLDR
This work analyzes the core protocols in distributed systems, and identifies key abstractions that can be efficiently implemented in network devices, given the limited hardware resources and restricted computational model, and can result in significant end-to-end performance improvements.
Building Atomic, Crash-Consistent Data Stores with Disaggregated Persistent Memory
TLDR
This paper explores different ways to organize DPM and to build data stores with DPM, and proposes three architectures of DPM: 1) compute nodes directly access DPM for data operations and communicate with a global metadata server for the control plane (DPM-Sep), 2) DPM-Direct has great small-size read but poor write performance; 3) D PM-Central has the best write performance when the scale of the cluster is small but performs poorly when the Scale increases.
Semeru: A Memory-Disaggregated Managed Runtime
TLDR
Semeru is presented, a distributed JVM that can dramatically improve the performance of managed cloud applications in a memory-disaggregated environment and possesses three major innovations: a universal Java heap, which provides a unified abstraction of virtual memory across CPU and memory servers and allows any legacy program to run without modifications.
Slashing the disaggregation tax in heterogeneous data centers with FractOS
TLDR
FractOS elevates devices to be first-class citizens, enabling direct peer-to-peer data transfers and task invocations among them, without centralized application and OS control, in a disaggregated data-center system.
Concordia: Distributed Shared Memory with In-Network Cache Coherence
TLDR
This paper proposes CONCORDIA, a DSM with fast in-network cache coherence backed by programmable switches, and introduces two techniques: an ownership migration mechanism to address the problem of limited memory capacity on switches and idempotent operations to handle packet loss in the case that switches are stateful.
ExtOS: Data-centric Extensible OS
TLDR
A top-to-bottom lean and optimized architecture is proposed, which allows applications to customize the OS kernel's IO subsystems with application-provided code, which enables sharing and high-performance IO among applications.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 69 REFERENCES
Scale-out NUMA
TLDR
The results based on cycle-accurate full-system simulation show that soNUMA performs remote reads at latencies that are within 4x of local DRAM, can fully utilize the available memory bandwidth, and can issue up to 10M remote memory operations per second per core.
Rack-scale disaggregated cloud data centers: The dReDBox project vision
For quite some time now, computing systems servers, whether low-power or high-end ones designs are created around a common design principle: the main-board and its hardware components form a
An operating system for multicore and clouds: mechanisms and implementation
TLDR
This work describes the mechanisms and implementation of a factored operating system named fos, a single system image operating system across both multicore and Infrastructure as a Service (IaaS) cloud systems, and provides early performance measurements of fos.
Making Cloud Easy: Design Considerations and First Components of a Distributed Operating System for Cloud
TLDR
This work argues that it is time to revisit ideas of Single System Image (SSI) concepts to simplify the management of Cloud execution contexts, and proposes a novel set of design principles inspired by earlier distributed operating system and SSI research.
The multikernel: a new OS architecture for scalable multicore systems
TLDR
This work investigates a new OS structure, the multikernel, that treats the machine as a network of independent cores, assumes no inter-core sharing at the lowest level, and moves traditional OS functionality to a distributed system of processes that communicate via message-passing.
The Case for RackOut: Scalable Data Serving Using Rack-Scale Systems
TLDR
This work introduces RackOut, a memory pooling technique that leverages the one-sided remote read primitive of emerging rack-scale systems to mitigate load imbalance while respecting service-level objectives, and develops a queuing model to evaluate the impact of RackOut at the datacenter scale.
Disaggregated memory for expansion and sharing in blade servers
TLDR
It is demonstrated that memory disaggregation can provide substantial performance benefits (on average 10X) in memory constrained environments, while the sharing enabled by the solutions can improve performance-per-dollar by up to 57% when optimizing memory provisioning across multiple servers.
Welcome to zombieland: practical and energy-efficient memory disaggregation in a datacenter
TLDR
An effortless way for disaggregating the CPU-memory couple, two of the most important resources in cloud computing, is proposed and can improve the energy efficiency of state-of-the-art consolidation techniques by up to 86%, with minimal additional complexity.
Flash storage disaggregation
TLDR
It is shown that Flash disaggregation allows scaling CPU and Flash resources independently in a cost effective manner through resource-efficient scale-out and is used to draw conclusions about data and control plane issues in remote storage.
Efficient Memory Disaggregation with Infiniswap
TLDR
The design and implementation of INFINISWAP is described, a remote memory paging system designed specifically for an RDMA network that increases the overall memory utilization of a cluster and works well at scale.
...
1
2
3
4
5
...