Provisioning of a shared server with guarantees is an important scheduling task that has led to significant work in a number of areas including link scheduling. Fair Queuing algorithms provide a method for proportionally sharing a single server among competing flows, however, they do not address the problem of sharing multiple servers. Multiserver systems arise in a number of applications including link aggregation, multiprocessors and multi-path storage I/O. In this paper we introduce a new service discipline for multi-server systems that provides guarantees for competing flows. We prove that this new service discipline is a close approximation of the idealized Generalized Processor Sharing (GPS) discipline. We calculate its maximum packet delay and service discrepancy with respect to GPS. We also discuss its relevance to several applications, in particular, Ethernet link aggregation.
Provisioning of a shared server with guarantees is an important scheduling task that has led to significant work in a number of areas including link scheduling. Fair Queuing algorithms provide a method for proportionally sharing a single server among competing flows, however, they do not address the problem of sharing multiple servers. Multiserver systems arise in a number of applications including link aggregation, multiprocessors and multi-path storage I/O. In this paper we introduce a new service discipline for multi-server systems that provides guarantees for competing flows. We prove that this new service discipline is a close approximation of the idealized Generalized Processor Sharing (GPS) discipline. We calculate its maximum packet delay and service discrepancy with respect to GPS. We also discuss its relevance to several applications, in particular, Ethernet link aggregation.
In this paper we argue that the best approach to providing Quality of Service (QoS) guarantees to current Internet services is to use admission control and traffic shaping techniques at the entrance points of Internet hosting sites. We propose a black-box approach that does not require knowledge, instrumentation, or modification of the system (hardware and software) that implements the services provided by the site.We maintain that such a non-intrusive QoS solution achieves better resource utilization, has lower cost, and is more flexible than the current approaches of physical partitioning and hardware overprovisioning. Furthermore, we contend that our solution is easier to deploy, less complex to implement, and easier to maintain than more intrusive approaches which embed the QoS logic into the operating system, distributed middleware, or application code. We demonstrate empirically that despite being decoupled from the internal mechanisms implementing the site, a black-box approach provides effective response times and capacity guarantees.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.