Towards the Performance Analysis of Apache Tez Applications
Requeno, José Ignacio (Universidad de Zaragoza, Dpto. Ingeniería de Sistemas, Spain) ; Gascón, Iñigo (Universidad de Zaragoza, Dpto. Ingeniería de Sistemas, Spain) ; Meseguer, José (Universidad de Zaragoza, Dpto. Ingeniería de Sistemas, Spain)Resumen:
Apache Tez is an application framework for large data processing using interactive queries. When a Tez developer faces the ful llment of performance requirements s/he needs to con gure and optimize the Tez application to speci c execution contexts. However, these are not easy tasks, though the Apache Tez con guration will im- pact in the performance of the application signi cantly. Therefore, we propose some steps, towards the modeling and simulation of Apache Tez applications, that can help in the performance assessment of Tez designs. For the modeling, we propose a UML pro le for Apache Tez. For the simulation, we propose to transform the stereotypes of the pro le into stochastic Petri nets, which can be eventually used for computing performance metrics.
Apache Tez is an application framework for large data processing using interactive queries. When a Tez developer faces the ful llment of performance requirements s/he needs to con gure and optimize the Tez application to speci c execution contexts. However, these are not easy tasks, though the Apache Tez con guration will im- pact in the performance of the application signi cantly. Therefore, we propose some steps, towards the modeling and simulation of Apache Tez applications, that can help in the performance assessment of Tez designs. For the modeling, we propose a UML pro le for Apache Tez. For the simulation, we propose to transform the stereotypes of the pro le into stochastic Petri nets, which can be eventually used for computing performance metrics.
Idioma: Inglés
DOI: 10.1145/3185768.3186284
Año: 2018
En: ICPE ’18 (2018, Berlin-Germany)
Financiación: info:eu-repo/grantAgreement/ES/MINECO/TIN2014-58457-R
Financiación: info:eu-repo/grantAgreement/EU/ERC-H2020/644869
Financiación: info:eu-repo/grantAgreement/ES/DGA/T27
Enlace permanente:
Debe reconocer adecuadamente la autoría, proporcionar un enlace a la licencia e indicar si se han realizado cambios. Puede hacerlo de cualquier manera razonable, pero no de una manera que sugiera que tiene el apoyo del licenciador o lo recibe por el uso que hace. No puede utilizar el material para una finalidad comercial. Si remezcla, transforma o crea a partir del material, no puede difundir el material modificado.Este artículo se encuentra en las siguientes colecciones:
Comunicaciones y ponencias
Registro creado el 2018-05-09, última modificación el 2018-05-09
