Xu, Meng
Email Address
ORCID
Disciplines
Search Results
Now showing 1 - 10 of 10
Publication Multi-Mode Virtualization for Soft Real-Time Systems(2018-04-01) Xu, Meng; Li, Haoran; Phan, Linh T.X.; Li, Chong; Lee, Insup; Lu, Chenyang; Sokolsky, Oleg; Gill, ChristopherReal-time virtualization is an emerging technology for embedded systems integration and latency-sensitive cloud applications. Earlier real-time virtualization platforms require offline configuration of the scheduling parameters of virtual machines (VMs) based on their worst-case workloads, but this static approach results in pessimistic resource allocation when the workloads in the VMs change dynamically. Here, we present Multi-Mode-Xen (M2-Xen), a real-time virtualization platform for dynamic real-time systems where VMs can operate in modes with different CPU resource requirements at run-time. M2-Xen has three salient capabilities: (1) dynamic allocation of CPU resources among VMs in response to their mode changes, (2) overload avoidance at both the VM and host levels during mode transitions, and (3) fast mode transitions between different modes. M2-Xen has been implemented within Xen 4.8 using the real-time deferrable server (RTDS) scheduler. Experimental results show that M2-Xen maintains real-time performance in different modes, avoids overload during mode changes, and performs fast mode transitions.Publication Cache-aware Interfaces for Compositional Real-Time Systems(2015-12-01) Phan, Linh T.X.; Xu, Meng; Lee, InsupInterface-based compositional analysis is by now a fairly established area of research in real-time systems. However, current research has not yet fully considered practical aspects, such as the effects of cache interferences on multicore platforms. This position paper discusses the analysis challenges and motivates the need for cache scheduling in this setting, and it highlights several research questions towards cache-aware interfaces for compositional systems on multicore platforms.Publication Cyber-Physical System Checkpointing and Recovery(2018-04-01) Kong, Fanxin; Xu, Meng; Weimer, James; Sokolsky, Oleg; Lee, InsupTransitioning to more open architectures has been making Cyber-Physical Systems (CPS) vulnerable to malicious attacks that are beyond the conventional cyber attacks. This paper studies attack-resilience enhancement for a system under emerging attacks in the environment of the controller. An effective way to address this problem is to make system state estimation accurate enough for control regardless of the compromised components. This work follows this way and develops a procedure named CPS checkpointing and recovery, which leverages historical data to recover failed system states. Specially, we first propose a new concept of physical-state recovery. The essential operation is defined as rolling the system forward starting from a consistent historical system state. Second, we design a checkpointing protocol that defines how to record system states for the recovery. The protocol introduces a sliding window that accommodates attack-detection delay to improve the correctness of stored states. Third, we present a use case of CPS checkpointing and recovery that deals with compromised sensor measurements. At last, we evaluate our design through conducting simulator-based experiments and illustrating the use of our design with an unmanned vehicle case study.Publication vCAT: Dynamic Cache Management Using CAT Virtualization(2017-04-01) Xu, Meng; Phan, Linh T.X.; Lee, Insup; Choi, Hyon-YoungThis paper presents vCAT, a novel design for dynamic shared cache management on multicore virtualization platforms based on Intel’s Cache Allocation Technology (CAT). Our design achieves strong isolation at both task and VM levels through cache partition virtualization, which works in a similar way as memory virtualization, but has challenges that are unique to cache and CAT. To demonstrate the feasibility and benefits of our design, we provide a prototype implementation of vCAT, and we present an extensive set of microbenchmarks and performance evaluation results on the PARSEC benchmarks and synthetic workloads, for both static and dynamic allocations. The evaluation results show that (i) vCAT can be implemented with minimal overhead, (ii) it can be used to mitigate shared cache interference, which could have caused task WCET increased by up to 7.2 x, (iii) static management in vCAT can increase system utilization by up to 7 x compared to a system without cache management; and (iv) dynamic management substantially outperforms static management in terms of schedulable utilization (increase by up to 3 x in our multi-mode example use case).Publication Overhead-Aware Compositional Analysis of Real-Time Systems(2013-04-01) Phan, Linh T.X.; Xu, Meng; Lee, Jaewoo; Lee, Insup; Sokolsky, OlegOver the past decade, interface-based compositional schedulability analysis has emerged as an effective method for guaranteeing real-time properties in complex systems. Several interfaces and interface computation methods have been developed, and they offer a range of tradeoffs between the complexity and the accuracy of the analysis. However, none of the existing methods consider platform overheads in the component interfaces. As a result, although the analysis results are sound in theory, the systems may violate their timing constraints when running on realistic platforms. This is due to various overheads, such as task release delays, interrupts, cache effects, and context switches. Simple solutions, such as increasing the interface budget or the tasks’ worst-case execution times by a fixed amount, are either unsafe (because of the overhead accumulation problem) or they waste a lot of resources. In this paper, we present an overhead-aware compositional analysis technique that can account for platform overheads in the representation and computation of component interfaces. Our technique extends previous overhead accounting methods, but it additionally addresses the new challenges that are specific to the compositional scheduling setting. To demonstrate that our technique is practical, we report results from an extensive evaluation on a realistic platform.Publication Cache-Aware Compositional Analysis of Real-Time Multicore Virtualization Platforms(2013-12-01) Xu, Meng; Phan, Linh T.X.; Lee, Insup; Sokolsky, Oleg; Xi, Sisu; Lu, Chenyang; Gill, ChristopherMulticore processors are becoming ubiquitous, and it is becoming increasingly common to run multiple real-time systems on a shared multicore platform. While this trend helps to reduce cost and to increase performance, it also makes it more challenging to achieve timing guarantees and functional isolation. One approach to achieving functional isolation is to use virtualization. However, virtualization also introduces many challenges to the multicore timing analysis; for instance, the overhead due to cache misses becomes harder to predict, since it depends not only on the direct interference between tasks but also on the indirect interference between virtual processors and the tasks executing on them. In this paper, we present a cache-aware compositional analysis technique that can be used to ensure timing guarantees of components scheduled on a multicore virtualization platform. Our technique improves on previous multicore compositional analyses by accounting for the cache-related overhead in the components’ interfaces, and it addresses the new virtualization-specific challenges in the overhead analysis. To demonstrate the utility of our technique, we report results from an extensive evaluation based on randomly generated workloads.Publication AutoV: An Automotive Testbed for Real-Time Virtualization(2017-04-01) Xu, Meng; Lee, InsupTiming isolation is critical for automotive systems. Real-time virtualization, such as RT-Xen, is a promising technique to integrate legacy automotive systems onto a powerful multi-core platform for achieving better performance and lower cost without breaking the timing isolation. However, the real-time virtualization has never been evaluated with real automotive applications in a non-simulation environment. In order to facilitate the evaluation of real-time virtualization for automotive systems, we propose the AutoV, an affordable and accessible automotive testbed for real-time virtualization. We present a case study to demonstrate the applications of the AutoV.Publication Analysis and Implementation of Global Preemptive Fixed-Priority Scheduling with Dynamic Cache Allocation(2016-04-01) Xu, Meng; Phan, Linh Thi Xuan; Lee, Insup; Choi, Hyon-YoungWe introduce gFPca, a cache-aware global pre-emptive fixed-priority (FP) scheduling algorithm with dynamic cache allocation for multicore systems, and we present its analysis and implementation. We introduce a new overhead-aware analysis that integrates several novel ideas to safely and tightly account for the cache overhead. Our evaluation shows that the proposed overhead-accounting approach is highly accurate, and that gFPca improves the schedulability of cache-intensive tasksets substantially compared to the cache-agnostic global FP algorithm. Our evaluation also shows that gFPca outperforms the existing cache-aware non- preemptive global FP algorithm in most cases. Through our implementation and empirical evaluation, we demonstrate the feasibility of cache-aware global scheduling with dynamic cache allocation and highlight scenarios in which gFPca is especially useful in practice.Publication RT-OpenStack: CPU Resource Management for Real-Time Cloud Computing(2015-06-01) Xi, Sisu; Xu, Meng; Li, Chong; Phan, Linh T.X.; Lu, Chenyang; Lee, Insup; Gill, Christopher D; Sokolsky, OlegClouds have become appealing platforms for not only general-purpose applications, but also real-time ones. However, current clouds cannot provide real-time performance to virtual machines (VMs). We observe the demand and the advantage of co-hosting real-time (RT) VMs with non-real-time (regular) VMs in a same cloud. RT VMs can benefit from the easily deployed, elastic resource provisioning provided by the cloud, while regular VMs effectively utilize remaining resources without affecting the performance of RT VMs through pro per resource management at both the cloud and the hypervisor levels. This paper presents RT-OpenStack, a cloud CPU resource management system for co-hosting real-time and regular VMs. RT-OpenStack entails three main contributions: (1) integration of a real-time hypervisor (RT-Xen) and a cloud management system (OpenStack) through a real-time resource interface; (2) a realtime VM scheduler to allow regular VMs to share hosts with RT VMs without interfering the real-time performance of RT VMs; and (3) a VM-to-host mapping strategy that provisions real-time performance to RT VMs while allowing effective resource sharing with regular VMs. Experimental results demonstrate that RTOpenStack can effectively improve the real-time performance of RT VMs while allowing regular VMs to fully utilize the remaining CPU resources.Publication Cache-Aware Compositional Analysis of Real-Time Multicore Virtualization Platforms(2015-11-01) Xu, Meng; Phan, Linh T.X.; Sokolsky, Oleg; Lee, Insup; Xi, Sisu; Lu, Chenyang; Gill, ChristopherMulticore processors are becoming ubiquitous, and it is becoming increasingly common to run multiple real-time systems on a shared multicore platform. While this trend helps to reduce cost and to increase performance, it also makes it more challenging to achieve timing guarantees and functional isolation. One approach to achieving functional isolation is to use virtualization. However, virtualization also introduces many challenges to the multicore timing analysis; for instance, the overhead due to cache misses becomes harder to predict, since it depends not only on the direct interference between tasks but also on the indirect interference between virtual processors and the tasks executing on them. In this paper, we present a cache-aware compositional analysis technique that can be used to ensure timing guarantees of components scheduled on a multicore virtualization platform. Our technique improves on previous multicore compositional analyses by accounting for the cache-related overhead in the components’ interfaces, and it addresses the new virtualization-specific challenges in the overhead analysis. To demonstrate the utility of our technique, we report results from an extensive evaluation based on randomly generated workloads