NDLI: A Case Against Tiny Tasks in Iterative Analytics

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

Performance clarity as a first-class design principle

Towards O(1) Memory

Thinking about Availability in Large Service Infrastructures

Towards Proving Optimistic Multicore Schedulers

Scalability Bugs: When 100-Node Testing is Not Enough

Verification in the Age of Microservices

Hypercallbacks: Decoupling Policy Decisions and Execution

Flash Drive Lifespan *is* a Problem

Preserving Hidden Data with an Ever-Changing Disk

It's Time to Think About an Operating System for Near Data Processing Architectures

A Clairvoyant Approach to Evaluating Software (In)Security

OmniX: an accelerator-centric OS for omni-programmable systems

Quantum Operating Systems

Consistency Oracles: Towards an Interactive and Flexible Consistency Model Specification

No!: Not Another Deep Learning Framework

Glimmers: Resolving the Privacy/Trust Quagmire

From Crash Consistency to Transactions

Real-Time Machine Learning: The Missing Pieces

Towards Automated Configuration of Systems with Non-Functional Constraints

Separating Translation from Protection in Address Spaces with Dynamic Remapping

The Game of Twenty Questions: Do You Know Where to Log?

Hardware is the new Software

Return of the Runtimes: Rethinking the Language Runtime System for the Cloud 3.0 Era

A Case Against Tiny Tasks in Iterative Analytics

Gray Failure: The Achilles' Heel of Cloud-Scale Systems

System Programming in Rust: Beyond Safety

Why Your Encrypted Database Is Not Secure

Will Serverless End the Dominance of Linux in the Cloud?

OS Support for Thread Migration and Distribution in the Fully Heterogeneous Datacenter

A Case Against Tiny Tasks in Iterative Analytics

Content Provider	ACM Digital Library
Author	Roy, Amitabha Dulloor, Subramanya R. Totoni, Ehsan
Abstract	Big data systems such as Spark are built around the idea of splitting an iterative parallel program into tiny tasks with other aspects of system design built around this basic design principle. Unfortunately, in spite of immense engineering effort, tiny tasks have unavoidably large overheads. We use the example of logistic regression -- a common machine learning primitive -- to compare the performance of Spark to different designs that converge to a hand-coded parallel MPI-based implementation. We conclude that Spark leaves orders of magnitude performance on the table, due to its insistence on setting the granularity of a task to a single iteration. We counter a common argument for the tiny task approach --namely better resilience to faults -- by demonstrating that optimum job checkpoint intervals are far longer than the duration of the tiny tasks favored in Spark's design. We propose an alternative approach that relies on an auto-parallelizing compiler tightly integrated with the MPI runtime, illustrating the opposite end of the spectrum where task granularities are as large as possible.
Starting Page	144
Ending Page	149
Page Count	6
File Format	PDF
ISBN	9781450350686
DOI	10.1145/3102980.3103004
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2017-05-07
Publisher Place	New York
Access Restriction	Subscribed
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

The case for tiny tasks in compute clusters.

Using learning analytics in iterative design of a digital modeling tool

Tiny Tasks – A Remedy for Synchronization Constraints in Multi-Server Systems

Endless horizons?: addressing current concerns about learning analytics

Examining the use of a visual analytics system for sensemaking tasks: case studies with domain experts.

Examining the use of a visual analytics system for sensemaking tasks: Case studies with domain experts (2012)

Reflecting on reflective writing analytics: assessment challenges and iterative evaluation of a prototype tool

Using learning analytics to assess students' behavior in open-ended programming tasks

VOTOR: conceptually simple remote voting against tiny tyrants

A Case Against Tiny Tasks in Iterative Analytics

Similar Documents

The case for tiny tasks in compute clusters.

Using learning analytics in iterative design of a digital modeling tool

Tiny Tasks – A Remedy for Synchronization Constraints in Multi-Server Systems

Endless horizons?: addressing current concerns about learning analytics

Examining the use of a visual analytics system for sensemaking tasks: case studies with domain experts.

Examining the use of a visual analytics system for sensemaking tasks: Case studies with domain experts (2012)

Reflecting on reflective writing analytics: assessment challenges and iterative evaluation of a prototype tool

Using learning analytics to assess students' behavior in open-ended programming tasks

VOTOR: conceptually simple remote voting against tiny tyrants

A Case Against Tiny Tasks in Iterative Analytics