Teaduslike töövoogude modelleerimine pilve jaoks
Date
2014
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Viimastel aastatel on hakanud teaduslikes kogukondades huvi pilvearvutuse vastu kasvama. Teaduskatsete läbiviimisel pilves on mitmeid eeliseid nagu elastsus, paindlikkus ja hooldatavus, kuid varasemad uuringud näitavad, et üks suurimaid probleeme teadusprogrammide jooksutamisel pilves on omavaheliste masinate andmevahetuse suurus. Üks lahendus sellele probleemile oleks tuvastada komponendid, mis omavahel palju suhtlevad ning panna nad pilves ühte kohta jooksma, et vähendada omavahelist andmevahetust. Antud bakalaureuse töös jagati (partitsioneeriti) Montage töövoo osad pilves asuvate virtuaalmasinate vahel ning rakendati valmis kirjutatud P2P süsteemi, et vähendada pilves olevat suhtlust. Tänu P2P süsteemile ja teadusprogrammi partitsioneerimisele vähendati kogu suhtlust pilves kuni 80%.
In recent years, cloud computing has raised significant interest in the scientific community. Running scientific experiments in the cloud has its advantages like elasticity, scalability and software maintenance. However, the communication latencies are observed to be the major hindrance for migrating scientific computing applications to the cloud. The problem escalates further when we consider scientific workflows, where significant data is exchanged across different tasks. One way to overcome this problem is to reduce the data communication by partitioning and scheduling the workflow and adapting a peer-to-peer file sharing among the nodes. Different size Montage workflows were considered for the analysis of this problem. From the study it was observed that the partitioning along with the peer-to-peer file sharing reduced the data communication in the cloud up to 80%
In recent years, cloud computing has raised significant interest in the scientific community. Running scientific experiments in the cloud has its advantages like elasticity, scalability and software maintenance. However, the communication latencies are observed to be the major hindrance for migrating scientific computing applications to the cloud. The problem escalates further when we consider scientific workflows, where significant data is exchanged across different tasks. One way to overcome this problem is to reduce the data communication by partitioning and scheduling the workflow and adapting a peer-to-peer file sharing among the nodes. Different size Montage workflows were considered for the analysis of this problem. From the study it was observed that the partitioning along with the peer-to-peer file sharing reduced the data communication in the cloud up to 80%