Cloud service providers could be doing themselves or their customers a disservice by relying on imprecise metrics for billing, says Carnegie Mellon University researcher Matthew Wachs. "Disk time is what costs, not I/Os or bytes, and that is what should be the metric in cloud storage systems," Wachs says.
Currently, infrastructure-as-a-service (IaaS) cloud storage providers typically bill on the amount of data being stored and the amount of data that is transferred to and from the cloud. However, the cost of handling that data may vary widely from one instance to another, resulting in tenant bills for storage access that has little or no relationship to the actual costs, Wachs says. This means that one customer executing several random reads and writes is using more of the system's resources than another customer who may be accessing the same amount of data through sequential accesses, while both customers are charged the same amount.
"This is an unsustainable approach because either the client or the provider will be unhappy," Wachs says. He suggests an alternative billing method based on the amount of time it takes the disk to read or write the material. "When we charge for disk time, and chose a rate for disk time that matches the cost for the provider, the costs are being recovered fairly," Wachs says.
From IDG News Service
View Full Article
No entries found