NDLI: The Case for RackOut: Scalable Data Serving Using Rack-Scale Systems

Please wait, while we are loading the content...

Why Does the Cloud Stop Computing?: Lessons from Hundreds of Service Outages

Optasia: A Relational Platform for Efficient Large-Scale Video Analytics

RAMinate: Hypervisor-based Virtualization for Hybrid Main Memory Systems

BASS: Improving I/O Performance for Cloud Block Storage via Byte-Addressable Storage Stack

CQSTR: Securing Cross-Tenant Applications with Cloud Containers

Disciplined Inconsistency with Consistency Types

ReStream: Accelerating Backtesting and Stream Replay with Serial-Equivalent Parallel Processing

SNC-Meister: Admitting More Tenants with Tail Latency SLOs

VNToR: Network Virtualization at the Top-of-Rack Switch

PipeGen: Data Pipe Generator for Hybrid Analytics

Automating Failure Testing Research at Internet Scale

A Fault-Tolerant Framework for Asynchronous Iterative Computations in Cloud Environments

A Case for Virtualizing Persistent Memory

The Case for RackOut: Scalable Data Serving Using Rack-Scale Systems

Radiatus: a Shared-Nothing Server-Side Web Architecture

Towards Weakly Consistent Local Storage Systems

STYX: Stream Processing with Trustworthy Cloud-based Execution

STeP: Scalable Tenant Placement for Managing Database-as-a-Service Deployments

Expeditus: Congestion-aware Load Balancing in Clos Data Center Networks

TR-Spark: Transient Computing for Big Data Analytics

Characterizing Private Clouds: A Large-Scale Empirical Analysis of Enterprise Clusters

Ako: Decentralised Deep Learning with Partial Gradient Exchange

Follow the Sun through the Clouds: Application Migration for Geographically Shifting Workloads

Grandet: A Unified, Economical Object Store for Web Applications

Tutamen: A Next-Generation Secret-Storage Platform

The Freeze-Frame File System

Trading Timeliness and Accuracy in Geo-Distributed Streaming Analytics

Principled workflow-centric tracing of distributed systems

Programming and Runtime Support to Blaze FPGA Accelerator Deployment at Datacenter Scale

Job-aware Scheduling in Eagle: Divide and Stick to Your Probes

Availability Knob: Flexible User-Defined Availability in the Cloud

Addressing the straggler problem for iterative convergent parallel ML

HIL: Designing an Exokernel for the Data Center

Randomized Algorithms for Dynamic Storage Load-Balancing

Privacy Preserving Collaboration in Bring-Your-Own-Apps

Adaptive Caching in Big SQL using the HDFS Cache

PerfOrator: eloquent performance models for Resource Optimization

Optimizing Interactive Development of Data-Intensive Applications

The Case for RackOut: Scalable Data Serving Using Rack-Scale Systems

Content Provider	ACM Digital Library
Author	Bugnion, Edouard Grot, Boris Daglis, Alexandros Falsafi, Babak Novakovic, Stanko
Abstract	To provide low latency and high throughput guarantees, most large key-value stores keep the data in the memory of many servers. Despite the natural parallelism across lookups, the load imbalance, introduced by heavy skew in the popularity distribution of keys, limits performance. To avoid violating tail latency service-level objectives, systems tend to keep server utilization low and organize the data in micro-shards, which provides units of migration and replication for the purpose of load balancing. These techniques reduce the skew, but incur additional monitoring, data replication and consistency maintenance overheads. In this work, we introduce 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. In RackOut, the data is aggregated at rack-scale granularity, with all of the participating servers in the rack jointly servicing all of the rack's micro-shards. We develop a queuing model to evaluate the impact of RackOut at the datacenter scale. In addition, we implement a RackOut proof-of-concept key-value store, evaluate it on two experimental platforms based on RDMA and Scale-Out NUMA, and use these results to validate the model. Our results show that RackOut can increase throughput up to 6x for RDMA and 8.6x for Scale-Out NUMA compared to a scale-out deployment, while respecting tight tail latency service-level objectives.
Starting Page	182
Ending Page	195
Page Count	14
File Format	PDF
ISBN	9781450345255
DOI	10.1145/2987550.2987577
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2016-10-05
Publisher Place	New York
Access Restriction	Subscribed
Subject Keyword	Rdma Data skew Rack-scale systems
Content Type	Text
Resource Type	Article

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Rack-Scale In-Memory Join Processing using RDMA

PROP: Using PCIe-Based RDMA to Accelerate Rack-Scale Communications in Data Centers

Scalable Cooperative Caching with RDMA-Based Directory Management for Large-Scale Data Processing

Poster: Scalable Cooperative Caching with RDMA-Based Directory Management for Large-Scale Data Processing

Performance Evaluation for Modular, Scalable Liquid-Rack Cooling Systems in Data Centers

Memory Management Strategies for Data Serving with RDMA

RDMA-Based Distributed Data Structures for Large-Scale Parallel Systems

Memory Management Strategies for Data Serving with RDMA

Memory Management Strategies for Data Serving with RDMA

The Case for RackOut: Scalable Data Serving Using Rack-Scale Systems

Similar Documents

Rack-Scale In-Memory Join Processing using RDMA

PROP: Using PCIe-Based RDMA to Accelerate Rack-Scale Communications in Data Centers

Scalable Cooperative Caching with RDMA-Based Directory Management for Large-Scale Data Processing

Poster: Scalable Cooperative Caching with RDMA-Based Directory Management for Large-Scale Data Processing

Performance Evaluation for Modular, Scalable Liquid-Rack Cooling Systems in Data Centers

Memory Management Strategies for Data Serving with RDMA

RDMA-Based Distributed Data Structures for Large-Scale Parallel Systems

Memory Management Strategies for Data Serving with RDMA

Memory Management Strategies for Data Serving with RDMA

The Case for RackOut: Scalable Data Serving Using Rack-Scale Systems