Results 1 - 10
of
12
Virtual-CPU Scheduling in the Quest Operating System
"... This paper describes the scheduling framework for a new operating system called “Quest”. The three main goals of Quest are to ensure safety, predictability and efficiency of software execution. For this paper, we focus on one aspect of predictability, involving the integrated management of tasks and ..."
Abstract
-
Cited by 13 (8 self)
- Add to MetaCart
(Show Context)
This paper describes the scheduling framework for a new operating system called “Quest”. The three main goals of Quest are to ensure safety, predictability and efficiency of software execution. For this paper, we focus on one aspect of predictability, involving the integrated management of tasks and I/O events such as interrupts. Quest’s scheduling infrastructure is based around the concept of a virtual CPU (VCPU). Using both Main and I/O VCPUs, we are able to separate the CPU bandwidth consumed by tasks from that used to complete I/O processing. We introduce a priority-inheritance bandwidth-preserving server policy for I/O management, called PIBS. We show how PIBS operates with lower cost and higher throughput than a comparable Sporadic Server for managing I/O transfers that require small bursts of CPU time. Using a hybrid system of Sporadic Servers for Main VCPUs, and PIBS for I/O VC-PUs, we show how to maintain temporal isolation between multiple tasks and I/O transfers from different devices. We believe Quest’s VCPU scheduling infrastructure is scalable enough to operate on future multi- and many-core systems supporting large numbers of threads. For a system of 24 VCPUs, we observe a CPU scheduling overhead of approximately 0.3 % when VCPU budget is managed in 1ms units. 1
HIRES: a System for Predictable Hierarchical Resource Management
"... Abstract—This paper presents HIRES, a system structured around predictable, hierarchical resource management (HRM). Applications and different subsystems use customized resource managers that control the allocation and usage of memory, CPU, and I/O. This increased resource management flexibility ena ..."
Abstract
-
Cited by 10 (0 self)
- Add to MetaCart
(Show Context)
Abstract—This paper presents HIRES, a system structured around predictable, hierarchical resource management (HRM). Applications and different subsystems use customized resource managers that control the allocation and usage of memory, CPU, and I/O. This increased resource management flexibility enables subsystems with different timing constraints to specialize resource management around meeting these requirements. In HIRES, subsystems delegate the management of resources to other subsystems, thus creating the resource management hierarchy. In delegating the control of resources, the subsystem focuses on providing isolation between competing subsystems. To make HRM both predictable and efficient, HIRES ensures that regardless of a subsystem’s depth in the hierarchy, the overheads of resource usage and control remain constant. In doing so, HIRES encourages HRM as a fundamental system design technique. Results show that HIRES has competitive performance with existing systems, and that HRM naturally provides both strong isolation guarantees, and flexible and efficient subsystem control over resources. I.
Mixed-Criticality Support in a High-Assurance, General-Purpose Microkernel
"... Abstract-We explore a model for mixed-criticality support in seL4, a high-assurance microkernel designed for real-world use. Specifically we investigate how the seL4 model can be extended without compromising its security properties and its generalpurpose nature, including high average-case perform ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Abstract-We explore a model for mixed-criticality support in seL4, a high-assurance microkernel designed for real-world use. Specifically we investigate how the seL4 model can be extended without compromising its security properties and its generalpurpose nature, including high average-case performance. The proposed model introduces reservations, with admission control performed at user level, similar to how seL4 handles spatial resources.
On Interrupt Scheduling based on Process Priority for Predictable Real-Time Behavior
"... Traditionally, kernel services are of a higher priority than user processes. The kernel can preempt the currently executed process in order to perform interrupt handling for the behalf of another process, even though the latter process is of a lower priority than the former. This can be viewed as pr ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Traditionally, kernel services are of a higher priority than user processes. The kernel can preempt the currently executed process in order to perform interrupt handling for the behalf of another process, even though the latter process is of a lower priority than the former. This can be viewed as priority inversion. We propose a new interrupt handling approach that couples interrupt scheduling with the priority of a process associated with the interrupt to handle. We present techniques to derive exact process priorities in handling interrupts for incoming network packets. The proposed approach has been implemented in Linux 2.6, and experiment results show that it reduces interference of lower priority processes to higher-priority process through interrupt handling. 1
Customizable and predictable synchronization in a component-based os
- in Proceedings of the International Conference on Embedded Systems and Applications (ESA
, 2010
"... Component-based operating systems enable embedded systems to adapt system policies, mechanisms, and abstrac-tions to the specific workloads and contexts of each system. The scope of an embedded system developer to customize the software of the system is often limited by the kernel abstrac-tions. For ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Component-based operating systems enable embedded systems to adapt system policies, mechanisms, and abstrac-tions to the specific workloads and contexts of each system. The scope of an embedded system developer to customize the software of the system is often limited by the kernel abstrac-tions. For example, synchronization and scheduling policies are often constrained to the static few provided by the kernel. As time-management is an essential aspect of many embed-ded systems, there is motivation to enable these systems to configure synchronization policies to their needs. In this paper, we present a component-based implemen-tation of system synchronization policies in the COMPOS-ITE OS. This implementation provides fault-isolation be-tween applications, synchronization mechanisms, and system schedulers while maintaining high levels of performance. Empirical evaluation demonstrates that the proposed prim-itives have performance comparable to a highly optimized, but uncustomizable futex mechanism in Linux. 1
Hybrid EDF Packet Scheduling for Real-Time Distributed Systems
"... Abstract—When multiple computational resource elements collaborate to handle events in a cyber-physical system, schedul-ing algorithms on these resource elements and the communi-cation delay between them contribute to the overall system utilization and schedulability. Employing earliest deadline fir ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—When multiple computational resource elements collaborate to handle events in a cyber-physical system, schedul-ing algorithms on these resource elements and the communi-cation delay between them contribute to the overall system utilization and schedulability. Employing earliest deadline first (EDF) scheduling in real-time cyber-physical systems has many challenges. First, the network layer of a resource has to interrupt and notify the scheduler about the deadlines of arrived messages. The randomness of interruption makes context switch costs unpredictable. Second, lack of globally synchronized clocks across resources renders event deadlines derived from local clocks and piggybacked in messages meaningless. Third, communication delay variances in a network increase the unpredictability of the system, e.g., when multiple resources transmit message bursts simultaneously. We address these challenges in this work. First, we combine EDF scheduling with periodic message transmission tasks. Then, we implement an EDF-based packet scheduler, which transmits packets considering event deadlines. Third, we employ bandwidth limitations on the transmission links of resources to decrease network contention and network delay variance. We have implemented our hybrid EDF scheduler in a real-time distributed storage system. We evaluate it on a cluster of nodes in a switched network environment resembling a distributed cyber-physical system to demonstrate the real-time capability of our scheduler. I.
Responsive and Enforced Interrupt Handling for
"... Abstract—The increasing performance of modern processors makes virtualization a viable solution for consolidating real-time systems into a single hardware platform. Although real-time task scheduling in a virtual machine can benefit from hierarchical scheduling, unbounded interrupt handling time and ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—The increasing performance of modern processors makes virtualization a viable solution for consolidating real-time systems into a single hardware platform. Although real-time task scheduling in a virtual machine can benefit from hierarchical scheduling, unbounded interrupt handling time and vulnerability to interrupt storms make practitioners hesitant to virtualize interrupt-driven real-time applications. In this paper, we propose vINT, an interrupt handling scheme designed for real-time system virtualization. vINT provides a pseudo-VCPU abstraction dedicated for interrupt handling, which overcomes the limits imposed by the timing parameters of virtual CPUs in an analyzable way. vINT also accounts for and enforces interrupt handling and resulting execution flows within a guest virtual machine. vINT does not require any change to the guest OS code, so it can be used for virtualizing proprietary, closed-source OSs. We analyze interrupt handling time as well as VCPU and task schedulability, with and without vINT. Our experimental results indicate that vINT achieves timely interrupt handling while providing as good task schedulability as when it is not used. Our case study based on a prototype implementation on the KVM hypervisor shows that vINT yields significant benefits in reducing interrupt handling time and in protecting real-time tasks against interrupt storms permeating into the virtual machine. I.
Integrated Task and Interrupt Management for Real-Time Systems
"... Real-time scheduling algorithms like RMA or EDF and their corresponding schedulability test have proven to be powerful tools for developing predictable real-time systems. However, the traditional interrupt man-agement model presents multiple inconsistencies that break the assumptions of many of the ..."
Abstract
- Add to MetaCart
Real-time scheduling algorithms like RMA or EDF and their corresponding schedulability test have proven to be powerful tools for developing predictable real-time systems. However, the traditional interrupt man-agement model presents multiple inconsistencies that break the assumptions of many of the real-time scheduling tests, diminishing its utility. In this article, we analyze these inconsistencies and present a model that resolves them by integrating interrupts and tasks in a single scheduling model. We then use the RMA theory to calculate the cost of the model and analyze the circumstances under which it can provide the most value. This model was implemented in a kernel module. The portability of the design of our module is discussed in terms of its independence from both the hardware and the kernel. We also discuss the imple-mentation issues of the model over conventional PC hardware, along with its cost and novel optimizations for reducing the overhead. Finally, we present our experimental evaluation to show evidence of its temporal determinism and overhead.
Software Architecture Challenges and Requirements for Transportation Cyber-Physical Systems
"... A new field of cyber-physical computing is now emerging, involving communication and processing of data exchanged between physical devices and systems. In the transportation cyber-physical system (CPS) domain, there are numerous challenges posed by avionics, automotive and rail applications. For exa ..."
Abstract
- Add to MetaCart
(Show Context)
A new field of cyber-physical computing is now emerging, involving communication and processing of data exchanged between physical devices and systems. In the transportation cyber-physical system (CPS) domain, there are numerous challenges posed by avionics, automotive and rail applications. For example, in the rail industry, monitoring and communication services are becoming increasingly im-
