NDLI: Efficient queue management for cluster scheduling

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

The Linux scheduler: a decade of wasted cores

GeePS: scalable deep learning on distributed GPUs with a GPU-specialized parameter server

Increasing large-scale data center capacity by statistical power control

A high performance file system for non-volatile main memory

A study of modern Linux API usage and compatibility: what to support when you're supporting

Juggler: a practical reordering resilient network stack for datacenters

On the capacity of thermal covert channels in multicores

PSLO: enforcing the $X^{th}$ percentile latency and throughput SLOs for consolidated VM storage

Type-aware transactions for faster concurrent code

TetriSched: global rescheduling with adaptive plan-ahead in dynamic heterogeneous clusters

vScale: automatic and efficient processor scaling for SMP virtual machines

STRADS: a distributed framework for scheduled model parallel machine learning

Exploiting variability for energy optimization of parallel programs

pVM: persistent virtual memory for efficient capacity scaling and object storage

BB: booting booster for consumer electronics with modern OS

Yoda: a highly available layer-7 load balancer

HAFT: hardware-assisted fault tolerance

Flash storage disaggregation

Practical condition synchronization for transactional memory

Efficient queue management for cluster scheduling

Application-specific quantum for multi-core platform scheduler

Flint: batch-interactive data-intensive processing on transient servers

Oasis: energy proportionality with hybrid server consolidation

zExpander: a key-value cache with both high performance and fewer misses

Shared address translation revisited

NChecker: saving mobile app developers from network disruptions

Fast and general distributed transactions using RDMA and HTM

Partial-parallel-repair (PPR): a distributed technique for repairing erasure coded storage

Parallel sections: scaling system-level data-structures

Picocenter: supporting long-lived, mostly-idle applications in cloud environments

Hold 'em or fold 'em?: aggregation queries under performance variations

Crayon: saving power through shape and color approximation on next-generation displays

Data tiering in heterogeneous memory systems

POSIX abstractions in modern operating systems: the old, the new, and the missing

TFC: token flow control in data center networks

Sinter: low-bandwidth remote access for the visually-impaired

Hardware read-write lock elision

Optimizing distributed actor systems for dynamic interactive services

Efficient queue management for cluster scheduling

Content Provider	ACM Digital Library
Author	Kandula, Srikanth Rasley, Jeff Karanasos, Konstantinos Fonseca, Rodrigo Vojnovic, Milan Rao, Sriram
Abstract	Job scheduling in Big Data clusters is crucial both for cluster operators' return on investment and for overall user experience. In this context, we observe several anomalies in how modern cluster schedulers manage queues, and argue that maintaining queues of tasks at worker nodes has significant benefits. On one hand, centralized approaches do not use worker-side queues. Given the inherent feedback delays that these systems incur, they achieve suboptimal cluster utilization, particularly for workloads dominated by short tasks. On the other hand, distributed schedulers typically do employ worker-side queuing, and achieve higher cluster utilization. However, they fail to place tasks at the best possible machine, since they lack cluster-wide information, leading to worse job completion time, especially for heterogeneous workloads. To the best of our knowledge, this is the first work to provide principled solutions to the above problems by introducing queue management techniques, such as appropriate queue sizing, prioritization of task execution via queue reordering, starvation freedom, and careful placement of tasks to queues. We instantiate our techniques by extending both a centralized (YARN) and a distributed (Mercury) scheduler, and evaluate their performance on a wide variety of synthetic and production workloads derived from Microsoft clusters. Our centralized implementation, Yaq-c, achieves 1.7x improvement on median job completion time compared to YARN, and our distributed one, Yaq-d, achieves 9.3x improvement over an implementation of Sparrow's batch sampling on Mercury.
Starting Page	1
Ending Page	15
Page Count	15
File Format	PDF
ISBN	9781450342407
DOI	10.1145/2901318.2901354
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2016-04-18
Publisher Place	New York
Access Restriction	Subscribed
Content Type	Text
Resource Type	Article

Central Library (ISO-9001:2015 Certified)
Indian Institute of Technology Kharagpur
Kharagpur, West Bengal, India | PIN - 721302

See location in the Map
03222 282435
Mail: support@ndl.gov.in

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