ビル設備機器の状態監視における仮想化技術の適用可能性の検討

IPSJ

Bibliographic Information

Other Title
  • A Measurement Study on Applying Hardware Virtualization for Building Facilities Monitoring

Search this article

Abstract

ビルの設備機器を遠隔から管理する遠隔ビル管理システム（BMS; Building Management System）には，ネットワークを介して機器の状態を取得するクローラと呼ばれるソフトウェアが存在する．計算機の仮想化（VM; Virtual Machine）を利用することで，遠隔BMSに必要な物理マシン数を減らせるが，仮想化によるオーバヘッドや複数VMの並列実行によりクローラの性能が低下する．遠隔BMSは99.999%という高い稼働率が要求されるため，仮想化がクローラの性能に与える影響を把握しておくことが重要である．本論文では，クローラをVM上で実行した場合の性能を評価する．この評価により，ミリ秒オーダでCPU使用率を計測する必要性や，VM間のCPU競合が性能に与える影響を明らかにする．

In a remote building management system (BMS) that manages facilities of buildings, there is an application called a crawler that collects statuses of facilities via a network. By running a crawler on a Virtual Machine (VM) for each building owner, the number of physical machines in the remote BMS can be reduced. However, performance of the crawler running on a VM could be degraded owing to overhead of virtualization and interference among VMs coexisting on the same physical machine. In addition, the crawler needs to meet its performance requirements with high probability, 99.999%, and therefore it is important to clarify the characteristics of the performance degradation. In this paper, we evaluate performance of the crawler running on a VM. From the evaluation, we confirm that 1) CPU usage measurement with millisecond granularity is important for appropriate CPU allocation and 2) CPU contention among VMs is one of the main factors of the performance degradation.

Journal

Keywords

Details 詳細情報について

Report a problem

Back to top