SEARCH · Searcharxiv

Results for “cs.OS”

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 559 records · Page 31Linked to original sources

arXiv2022

Rapid Recovery of Program Execution Under Power Failures for Embedded Systems with NVM

After power is switched on, recovering the interrupted program from the initial state can cause negative impact. Some programs are even unrecoverable. To rapid recovery of program execution under power failures, the execution states of checkpoints are backed up by NVM under power failures for embedded systems with NVM. However, frequent checkpoints will shorten the lifetime of the NVM and incur significant write overhead. In this paper, the technique of checkpoint setting triggered by function calls is proposed to reduce the write on NVM. The evaluation results show an average of 99.8% and 80.5$% reduction on NVM backup size for stack backup, compared to the log-based method and step-based method. In order to better achieve this, we also propose pseudo-function calls to increase backup points to reduce recovery costs, and exponential incremental call-based backup methods to reduce backup costs in the loop. To further avoid the content on NVM is cluttered and out of NVM, a method to clean the contents on the NVM that are useless for restoration is proposed. Based on aforementioned problems and techniques, the recovery technology is proposed, and the case is used to analyze how to recover rapidly under different power failures.

cs.OS↗

arXiv2022

Multi-level Explanation of Deep Reinforcement Learning-based Scheduling

Dependency-aware job scheduling in the cluster is NP-hard. Recent work shows that Deep Reinforcement Learning (DRL) is capable of solving it. It is difficult for the administrator to understand the DRL-based policy even though it achieves remarkable performance gain. Therefore the complex model-based scheduler is not easy to gain trust in the system where simplicity is favored. In this paper, we give the multi-level explanation framework to interpret the policy of DRL-based scheduling. We dissect its decision-making process to job level and task level and approximate each level with interpretable models and rules, which align with operational practices. We show that the framework gives the system administrator insights into the state-of-the-art scheduler and reveals the robustness issue in regards to its behavior pattern.

cs.DC↗

arXiv2022

HMM-V: Heterogeneous Memory Management for Virtualization

The memory demand of virtual machines (VMs) is increasing, while DRAM has limited capacity and high power consumption. Non-volatile memory (NVM) is an alternative to DRAM, but it has high latency and low bandwidth. We observe that the VM with heterogeneous memory may incur up to a $1.5\times$ slowdown compared to a DRAM VM, if not managed well. However, none of the state-of-the-art heterogeneous memory management designs are customized for virtualization on a real system. In this paper, we propose HMM-V, a Heterogeneous Memory Management system for Virtualization. HMM-V automatically determines page hotness and migrates pages between DRAM and NVM to achieve performance close to the DRAM system. First, HMM-V tracks memory accesses through page table manipulation, but reduces the cost by leveraging Intel page-modification logging (PML) and a multi-level queue. Second, HMM-V quantifies the ``temperature'' of page and determines the hot set with bucket-sorting. HMM-V then efficiently migrates pages with minimal access pause and handles dirty pages with the assistance of PML. Finally, HMM-V provides pooling management to balance precious DRAM across multiple VMs to maximize utilization and overall performance. HMM-V is implemented on a real system with Intel Optane DC persistent memory. The four-VM co-running results show that HMM-V outperforms NUMA balancing and hardware management (Intel Optane memory mode) by $51\%$ and $31\%$, respectively.

cs.OS↗

arXiv2022

Paging with Succinct Predictions

Paging is a prototypical problem in the area of online algorithms. It has also played a central role in the development of learning-augmented algorithms -- a recent line of research that aims to ameliorate the shortcomings of classical worst-case analysis by giving algorithms access to predictions. Such predictions can typically be generated using a machine learning approach, but they are inherently imperfect. Previous work on learning-augmented paging has investigated predictions on (i) when the current page will be requested again (reoccurrence predictions), (ii) the current state of the cache in an optimal algorithm (state predictions), (iii) all requests until the current page gets requested again, and (iv) the relative order in which pages are requested. We study learning-augmented paging from the new perspective of requiring the least possible amount of predicted information. More specifically, the predictions obtained alongside each page request are limited to one bit only. We consider two natural such setups: (i) discard predictions, in which the predicted bit denotes whether or not it is ``safe'' to evict this page, and (ii) phase predictions, where the bit denotes whether the current page will be requested in the next phase (for an appropriate partitioning of the input into phases). We develop algorithms for each of the two setups that satisfy all three desirable properties of learning-augmented algorithms -- that is, they are consistent, robust and smooth -- despite being limited to a one-bit prediction per request. We also present lower bounds establishing that our algorithms are essentially best possible.

cs.LG↗

arXiv2022

Microsoft Defender Will Be Defended: MemoryRanger Prevents Blinding Windows AV

Windows OS is facing a huge rise in kernel attacks. An overview of popular techniques that result in loading kernel drivers will be presented. One of the key targets of modern threats is disabling and blinding Microsoft Defender, a default Windows AV. The analysis of recent driver-based attacks will be given, the challenge is to block them. The survey of user- and kernel-level attacks on Microsoft Defender will be given. One of the recently published attackers techniques abuses Mandatory Integrity Control (MIC) and Security Reference Monitor (SRM) by modifying Integrity Level and Debug Privileges for the Microsoft Defender via syscalls. However, this user-mode attack can be blocked via the Windows 'trust labels' mechanism. The presented paper discovered the internals of MIC and SRM, including the analysis of Microsoft Defender during malware detection. We show how attackers can attack Microsoft Defender using a kernel-mode driver. This driver modifies the fields of the Token structure allocated for the Microsoft Defender application. The presented attack resulted in disabling Microsoft Defender, without terminating any of its processes and without triggering any Windows security features, such as PatchGuard. The customized hypervisor-based solution named MemoryRanger was used to protect the Windows Defender kernel structures. The experiments show that MemoryRanger successfully restricts access to the sensitive kernel data from illegal access attempts with affordable performance degradation.

cs.CR↗

arXiv2022

Femto-Containers: Lightweight Virtualization and Fault Isolation For Small Software Functions on Low-Power IoT Microcontrollers

Low-power operating system runtimes used on IoT microcontrollers typically provide rudimentary APIs, basic connectivity and, sometimes, a (secure) firmware update mechanism. In contrast, on less constrained hardware, networked software has entered the age of serverless, microservices and agility. With a view to bridge this gap, in the paper we design Femto-Containers, a new middleware runtime which can be embedded on heterogeneous low-power IoT devices. Femto-Containers enable the secure deployment, execution and isolation of small virtual software functions on low-power IoT devices, over the network. We implement Femto-Containers, and provide integration in RIOT, a popular open source IoT operating system. We then evaluate the performance of our implementation, which was formally verified for fault-isolation, guaranteeing that RIOT is shielded from logic loaded and executed in a Femto-Container. Our experiments on various popular microcontroller architectures (Arm Cortex-M, ESP32 and RISC-V) show that Femto-Containers offer an attractive trade-off in terms of memory footprint overhead, energy consumption, and security

cs.OS↗

arXiv2022

Ecovisor: A Virtual Energy System for Carbon-Efficient Applications

Cloud platforms' rapid growth is raising significant concerns about their carbon emissions. To reduce emissions, future cloud platforms will need to increase their reliance on renewable energy sources, such as solar and wind, which have zero emissions but are highly unreliable. Unfortunately, today's energy systems effectively mask this unreliability in hardware, which prevents applications from optimizing their carbon-efficiency, or work done per kilogram of carbon emitted. To address this problem, we design an "ecovisor", which virtualizes the energy system and exposes software-defined control of it to applications. An ecovisor enables each application to handle clean energy's unreliability in software based on its own specific requirements. We implement a small-scale ecovisor prototype that virtualizes a physical energy system to enable software-based application-level i) visibility into variable grid carbon-intensity and renewable generation and ii) control of server power usage and battery charging/discharging. We evaluate the ecovisor approach by showing how multiple applications can concurrently exercise their virtual energy system in different ways to better optimize carbon-efficiency based on their specific requirements compared to a general system-wide policy.

cs.OS↗

arXiv2022

MUSTACHE: Multi-Step-Ahead Predictions for Cache Eviction

In this work, we propose MUSTACHE, a new page cache replacement algorithm whose logic is learned from observed memory access requests rather than fixed like existing policies. We formulate the page request prediction problem as a categorical time series forecasting task. Then, our method queries the learned page request forecaster to obtain the next $k$ predicted page memory references to better approximate the optimal Bélády's replacement algorithm. We implement several forecasting techniques using advanced deep learning architectures and integrate the best-performing one into an existing open-source cache simulator. Experiments run on benchmark datasets show that MUSTACHE outperforms the best page replacement heuristic (i.e., exact LRU), improving the cache hit ratio by 1.9% and reducing the number of reads/writes required to handle cache misses by 18.4% and 10.3%.

cs.OS↗

arXiv2022

Rescuing the End-user systems from Vulnerable Applications using Virtualization Techniques

In systems owned by normal end-users, many times security attacks are mounted by sneaking in malicious applications or exploiting existing software vulnerabilities through security non-conforming actions of users. Virtualization approaches can address this problem by providing a quarantine environment for applications, malicious devices, and device drivers, which are mostly used as entry points for security attacks. However, the existing methods to provide quarantine environments using virtualization are not transparent to the user, both in terms of application interface transparency and file system transparency. Further, software configuration level solutions like remote desktops and remote application access mechanisms combined with shared file systems do not meet the user transparency and security requirements. We propose qOS, a VM-based solution combined with certain OS extensions to meet the security requirements of end-point systems owned by normal users, in a transparent and efficient manner. We demonstrate the efficacy of qOS by empirically evaluating the prototype implementation in the Linux+KVM system in terms of efficiency, security, and user transparency.

cs.CR↗

arXiv2022

MeSHwA: The case for a Memory-Safe Software and Hardware Architecture for Serverless Computing

Motivated by developer productivity, serverless computing, and microservices have become the de facto development model in the cloud. Microservices decompose monolithic applications into separate functional units deployed individually. This deployment model, however, costs CSPs a large infrastructure tax of more than 25%. To overcome these limitations, CSPs shift workloads to Infrastructure Processing Units (IPUs) like Amazon's Nitro or, complementary, innovate by building on memory-safe languages and novel software abstractions. Based on these trends, we hypothesize a \arch providing a general-purpose runtime environment to specialize functionality when needed and strongly isolate components. To achieve this goal, we investigate building a single address space OS or a multi-application library OS, possible hardware implications, and demonstrate their capabilities, drawbacks and requirements. The goal is to bring the advantages to all application workloads including legacy and memory-unsafe applications, and analyze how hardware may improve the efficiency and security.

cs.OS↗

arXiv2022

Unsafe at Any Copy: Name Collisions from Mixing Case Sensitivities

File name confusion attacks, such as malicious symbolic links and file squatting, have long been studied as sources of security vulnerabilities. However, a recently emerged type, i.e., case-sensitivity-induced name collisions, has not been scrutinized. These collisions are introduced by differences in name resolution under case-sensitive and case-insensitive file systems or directories. A prominent example is the recent Git vulnerability (CVE-2021-21300) which can lead to code execution on a victim client when it clones a maliciously crafted repository onto a case-insensitive file system. With trends including ext4 adding support for per-directory case-insensitivity and the broad deployment of the Windows Subsystem for Linux, the prerequisites for such vulnerabilities are increasingly likely to exist even in a single system. In this paper, we make a first effort to investigate how and where the lack of any uniform approach to handling name collisions leads to a diffusion of responsibility and resultant vulnerabilities. Interestingly, we demonstrate the existence of a range of novel security challenges arising from name collisions and their inconsistent handling by low-level utilities and applications. Specifically, our experiments show that utilities handle many name collision scenarios unsafely, leaving the responsibility to applications whose developers are unfortunately not yet aware of the threats. We examine three case studies as a first step towards systematically understanding the emerging type of name collision vulnerability.

cs.CR↗

arXiv2022

DisTRaC: Accelerating High Performance Compute Processing for Temporary Data Storage

High Performance Compute (HPC) clusters often produce intermediate files as part of code execution and message passing is not always possible to supply data to these cluster jobs. In these cases, I/O goes back to central distributed storage to allow cross node data sharing. These systems are often high performance and characterised by their high cost per TB and sensitivity to workload type such as being tuned to small or large file I/O. However, compute nodes often have large amounts of RAM, so when dealing with intermediate files where longevity or reliability of the system is not as important, local RAM disks can be used to obtain performance benefits. In this paper we show how this problem was tackled by creating a RAM block that could interact with the object storage system Ceph, as well as creating a deployment tool to deploy Ceph on HPC infrastructure effectively. This work resulted in a system that was more performant than the central high performance distributed storage system used at Diamond reducing I/O overhead and processing time for Savu, a tomography data processing application, by 81.04% and 8.32% respectively.

cs.DC↗

arXiv2022

HyperEnclave: An Open and Cross-platform Trusted Execution Environment

A number of trusted execution environments (TEEs) have been proposed by both academia and industry. However, most of them require specific hardware or firmware changes and are bound to specific hardware vendors (such as Intel, AMD, ARM, and IBM). In this paper, we propose HyperEnclave, an open and cross-platform process-based TEE that relies on the widely-available virtualization extension to create the isolated execution environment. In particular, HyperEnclave is designed to support the flexible enclave operation modes to fulfill the security and performance demands under various enclave workloads. We provide the enclave SDK to run existing SGX programs on HyperEnclave with little or no source code changes. We have implemented HyperEnclave on commodity AMD servers and deployed the system in a world-leading FinTech company to support real-world privacy-preserving computations. The evaluation on both micro-benchmarks and application benchmarks shows the design of HyperEnclave introduces only a small overhead.

cs.CR↗

arXiv2022

Automated Cache for Container Executables

Linux container technologies such as Docker and Singularity offer encapsulated environments for easy execution of software. In high performance computing, this is especially important for evolving and complex software stacks with conflicting dependencies that must co-exist. Singularity Registry HPC ("shpc") was created as an effort to install containers in this environment as modules, seamlessly allowing for typically hidden executables inside containers to be presented to the user as commands, and as such significantly simplifying the user experience. A remaining challenge, however, is deriving the list of important executables in the container. In this work, we present new automation and methods that allow for not only discovering new containers in large community sets, but also deriving container entries with important executables. With this work we have added over 8,000 containers from the BioContainers community that can be maintained and updated by the software automation over time. All software is publicly available on the GitHub platform, and can be beneficial to container registries and infrastructure providers for automatically generating container modules to lower the usage entry barrier and improve user experience.

cs.OS↗

arXiv2022

E2C: A Visual Simulator for Heterogeneous Computing Systems

Heterogeneity has been an indispensable aspect of distributed computing throughout the history of these systems. In particular, with the increasing prevalence of accelerator technologies (e.g., GPUs and TPUs) and the emergence of domain-specific computing via ASICs and FPGA, the matter of heterogeneity and harnessing it has become a more critical challenge than ever before. Harnessing system heterogeneity has been a longstanding challenge in distributed systems and has been investigated extensively in the past. Making use of real infrastructure (such as those offered by the public cloud providers) for benchmarking the performance of heterogeneous machines, for different applications, with respect to different objectives, and under various workload intensities is cost- and time-prohibitive. To mitigate this burden, we develop an open-source simulation tool, called E2C, that can help researchers and practitioners study any type of heterogeneous computing system and measure its performance under various system configurations. E2C has an intuitive graphical user interface (GUI) that enables its users to easily examine system-level solutions (scheduling, load balancing, scalability, etc.) in a controlled environment within a short time and at no cost. In particular, E2C offers the following features: (i) simulating a heterogeneous computing system; (ii) implementing a newly developed scheduling method and plugging it into the system, (iii) measuring energy consumption and other output-related metrics; and (iv) powerful visual aspects to ease the learning curve for students. Potential users of E2C can be undergraduate and graduate students in computer science/engineering, researchers, and practitioners.

cs.DC↗

arXiv2022

MProtect: Operating System Memory Management without Access

Modern operating systems (OSes) have unfettered access to application data, assuming that applications trust them. This assumption, however, is problematic under many scenarios where either the OS provider is not trustworthy or the OS can be compromised due to its large attack surface. Our investigation began with the hypothesis that unfettered access to memory is not fundamentally necessary for the OS to perform its own job, including managing the memory. The result is a system called MProtect that leverages a small piece of software running at a higher privilege level than the OS. MProtect protects the entire user space of a process, requires only a small modification to the OS, and supports major architectures such as ARM, x86 and RISC-V. Unlike prior works that resorted to nested virtualization, which is often undesirable in mobile and embedded systems, MProtect mediates how the OS accesses the memory and handles exceptions. We report an implementation of MProtect called MGuard with ARMv8/Linux and evaluate its performance with both macro and microbenchmarks. We show MGuard has a runtime TCB 2~3 times smaller than related systems and enjoys competitive performance while supporting legitimate OS access to the user space.

cs.OS↗

arXiv2023

Age-Optimal Multi-Channel-Scheduling under Energy and Tolerance Constraints

We study the optimal scheduling problem where n source nodes attempt to transmit updates over L shared wireless on/off fading channels to optimize their age performance under energy and age-violation tolerance constraints. Specifically, we provide a generic formulation of age-optimization in the form of a constrained Markov Decision Processes (CMDP), and obtain the optimal scheduler as the solution of an associated Linear Programming problem. We investigate the characteristics of the optimal single-user multi-channel scheduler for the important special cases of average-age and violation-rate minimization. This leads to several key insights on the nature of the optimal allocation of the limited energy, where a usual threshold-based policy does not apply and will be useful in guiding scheduler designers. We then investigate the stability region of the optimal scheduler for the multi-user case. We also develop an online scheduler using Lyapunov-drift-minimization methods that do not require the knowledge of channel statistics. Our numerical studies compare the stability region of our online scheduler to the optimal scheduler to reveal that it performs closely with unknown channel statistics.

cs.IT↗

arXiv2023

SFP: Providing System Call Flow Protection against Software and Fault Attacks

With the improvements in computing technologies, edge devices in the Internet-of-Things have become more complex. The enabler technology for these complex systems are powerful application core processors with operating system support, such as Linux. While the isolation of applications through the operating system increases the security, the interface to the kernel poses a new threat. Different attack vectors, including fault attacks and memory vulnerabilities, exploit the kernel interface to escalate privileges and take over the system. In this work, we present SFP, a mechanism to protect the execution of system calls against software and fault attacks providing integrity to user-kernel transitions. SFP provides system call flow integrity by a two-step linking approach, which links the system call and its origin to the state of control-flow integrity. A second linking step within the kernel ensures that the right system call is executed in the kernel. Combining both linking steps ensures that only the correct system call is executed at the right location in the program and cannot be skipped. Furthermore, SFP provides dynamic CFI instrumentation and a new CFI checking policy at the edge of the kernel to verify the control-flow state of user programs before entering the kernel. We integrated SFP into FIPAC, a CFI protection scheme exploiting ARM pointer authentication. Our prototype is based on a custom LLVM-based toolchain with an instrumented runtime library combined with a custom Linux kernel to protect system calls. The evaluation of micro- and macrobenchmarks based on SPEC 2017 show an average runtime overhead of 1.9 % and 20.6 %, which is only an increase of 1.8 % over plain control-flow protection. This small impact on the performance shows the efficiency of SFP for protecting all system calls and providing integrity for the user-kernel transitions.

cs.CR↗