CPU Accounting for Multicore Processors

TitleCPU Accounting for Multicore Processors
Publication TypeJournal Article
Year of Publication2012
AuthorsLuque, C., Moretó M., Cazorla F. J., Gioiosa R., Buyuktosunoglu A., & Valero M.
Published inIEEE Transactions on Computers. Vol. 61
Other Numbers3258
Abstract

In single-threaded processors and Symmetric Multiprocessors the execution time of a task depends on the other tasks itruns with (the workload), since the Operating System (OS) time shares the CPU(s) between tasks in the workload. However, the timeaccounted to a task is roughly the same regardless of the workload in which the task runs in, since the OS takes into account thoseperiods in which the task is not scheduled onto a CPU. Chip Multiprocessors (CMPs) introduce complexities when accounting CPUutilization, since the CPU time to account to a task not only depends on the time that the task is scheduled onto a CPU, but also on theamount of hardware resources it receives during that period. And given that in a CMP hardware resources are dynamically sharedbetween tasks, the CPU time accounted to a task in a CMP depends on the workload it executes in. This is undesirable because thesame task with the same input data set may be accounted differently depending on the workload it executes. In this paper, we identifyhow an inaccurate measurement of the CPU utilization affects several key aspects of the system such as OS statistics or the chargingmechanism in data centers. We propose a new hardware CPU accounting mechanism to improve the accuracy when measuring theCPU utilization in CMPs and compare it with the previous accounting mechanisms. Our results show that currently known mechanismslead to a 16 percent average error when it comes to CPU utilization accounting. Our proposal reduces this error to less than2.8 percent in a modeled 8-core processor system.

Acknowledgment

This work was partially supported by funding provided to ICSI by the Department of Universities, Research and Information Society (DURSI) of the Catalan Government (grant 2010-BE-00352).

URLhttps://www.icsi.berkeley.edu/pubs/arch/cpuaccounting12.pdf
Bibliographic Notes

IEEE Transactions on Computers. Vol. 61, Issue 2

Abbreviated Authors

C. Luque, M. Moretó, F. J. Cazorla, R. Gioiosa, A. Buyuktosunoglu, and M. Valero

ICSI Research Group

Architecture

ICSI Publication Type

Article in journal or magazine