NDLI: Topology-aware resource management for HPC applications

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

Multi-valued Asynchronous Reliable Broadcast with a Strict Honest Majority

Local Checkability in Dynamic Networks

Time-communication trade-offs for minimum spanning tree construction

Accountability in Dynamic Networks

Scalable MapReduce-based Fuzzy Min-Max Neural Network for Pattern Classification

Topology-aware resource management for HPC applications

An Architecture for SDN Based Sensor Networks

PPRP: Predicted Position Based Routing Protocol Using Kalman Filter for Vehicular Ad-hoc Network

Total Order Reliable Convergecast in WBAN

An NDNoT based Efficient Object Searching Scheme for Smart Home using RFIDs

Minimizing Network Traffic Features for Android Mobile Malware Detection

Implementation and Performance Evaluation of Name-based Forwarding Schemes in V-NDN

A Resilient Self-Organizing Offshore Communication Network for Fishermen

Practical Multi-threaded Graph Coloring Algorithms for Shared Memory Architecture

Reinforcing Immutability of Permissioned Blockchains with Keyless Signatures' Infrastructure

Probabilistic Byzantine Tolerance Scheduling in Hybrid Cloud Environments

Distributed Computation of Mixing Time

Lock-free Linearizable 1-Dimensional Range Queries

Secure Multiparty Construction of a Distributed Social Network

Feasibility of Fog Computing Deployment based on Docker Containerization over RaspberryPi

Optimized Offloading Using Local Clusters

FastRank: Practical Lightweight Tolerance to Rational Behaviour in Edge Assisted Streaming

A Novel Priority Based Exigent Data Diffusion Approach for Urban VANets

Best Effort Broadcast under Cascading Failures in Interdependent Networks

Efficient Algorithms for Power Maximization in the Vector Model for Wireless Energy Transfer

Contemporary IT Security for Military Online Collaboration Platforms

A Planning Based Approach for Context Aware Services Composition in Pervasive Systems: Short Paper

Performance Assessment of an Extremely Challenged Mobile Infrastructure Network over the Oceans

Balancing Maximal Independent Sets using Hadoop

A Self-Stabilizing Minimal k-Grouping Algorithm

Fault-tolerant Gathering of Semi-synchronous Robots

Efficient Algorithms for Predicate Detection using Hybrid Logical Clocks

Energy-Aware Scheduling of Periodic Conditional Task Graphs on MPSoCs

Improved Write Access Control and Stronger Freshness Guarantee to Outsourced Data

Dynamic Pricing for Maximizing Cloud Revenue: A Column Generation Approach

An Energy-efficient and Buffer-aware Routing Protocol for Opportunistic Smart Traffic Management

SER Performance of OFDM-Based AF and DF Cooperative Networks over Asymmetric Fading Channels

Are We Birds of the Same Feather?

Coalitional Game Theory based Cooperative Spectrum Sensing in CRNs

Exploring the Impact of Connectivity on Dissemination of Post Disaster Situational Data over DTN

On Diameter Based Community Structure Identification in Networks

Fault-Tolerant Gathering of Mobile Robots with Weak Multiplicity Detection

Exact, Fast and Scalable Parallel DBSCAN for Commodity Platforms

Disaster-aware WDM network design for data centres

Towards Smart City: Sensing Air Quality in City based on Opportunistic Crowd-sensing

Energy Aware Cluster Head Load Balancing Scheme for Heterogeneous Wireless Ad Hoc Network

Topology-aware resource management for HPC applications

Content Provider	ACM Digital Library
Author	Villiermet, Adèle Mercier, Guillaume Jeannot, Emmanuel Georgiou, Yiannis
Abstract	The Resource and Job Management System (RJMS) is a crucial system software part of the HPC stack. It is responsible for efficiently delivering computing power to applications in supercomputing environments. Its main intelligence relies on resource selection techniques to find the most adapted resources to schedule the users' jobs. Improper resource selection operations may lead to poor performance executions and global system utilization along with an increase of the system fragmentation and jobs starvation. These phenomena play a role in the increase of the platforms' total cost of ownership and should be minimized. This paper introduces a new method that takes into account the topology of the machine and the application characteristics to determine the best choice among the available nodes of the platform based upon their position within the network and taking into account the applications communication pattern. To validate our approach, we integrate this algorithm as a plugin for Slurm, a popular and widespread HPC resource and job management system (RJMS). We assess our plugin with different optimization schemes by comparing with the default topology-aware Slurm algorithm using both emulation and simulation of a large-scale platform, and by carrying out experiments in a real cluster. We show that transparently taking into account the job communication pattern and the topology allows for relevant performance gains.
Starting Page	1
Ending Page	10
Page Count	10
File Format	PDF
ISBN	9781450348393
DOI	10.1145/3007748.3007768
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2017-01-05
Publisher Place	New York
Access Restriction	Subscribed
Subject Keyword	Slurm Job allocation Topology-aware placement Scheduling Resource management
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

Topology-aware resource management for HPC applications

Topology-aware resource management for HPC applications

Large-scale experiment for topology-aware resource management

Topologically Aware Job Scheduling for SLURM

A2L2: An Application Aware Flexible HPC Scheduling Model for Low-Latency Allocation

Large-scale experiment for topology-aware resource management

HPC-Aware VM Placement in Infrastructure Clouds

Enabling Workflow-Aware Scheduling on HPC Systems

Evaluating scalability and efficiency of the resource and job management system on large hpc clusters.

Topology-aware resource management for HPC applications

Similar Documents

Topology-aware resource management for HPC applications

Topology-aware resource management for HPC applications

Large-scale experiment for topology-aware resource management

Topologically Aware Job Scheduling for SLURM

A2L2: An Application Aware Flexible HPC Scheduling Model for Low-Latency Allocation

Large-scale experiment for topology-aware resource management

HPC-Aware VM Placement in Infrastructure Clouds

Enabling Workflow-Aware Scheduling on HPC Systems

Evaluating scalability and efficiency of the resource and job management system on large hpc clusters.

Topology-aware resource management for HPC applications