SEARCH · Searcharxiv
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.
A file system standard for use with write-once media such as digital compact disks is proposed. The file system is designed to work with any operating system and a variety of physical media. Although the implementation is simple, it provides a a full-featured and high-performance alternative to conventional file systems on traditional, multiple-write media such as magnetic disks.
Several emerging technologies for byte-addressable non-volatile memory (NVM) have been considered to replace DRAM as the main memory in computer systems during the last years. The disadvantage of a lower write endurance, compared to DRAM, of NVM technologies like Phase-Change Memory (PCM) or Ferroelectric RAM (FeRAM) has been addressed in the literature. As a solution, in-memory wear-leveling techniques have been proposed, which aim to balance the wear-level over all memory cells to achieve an increased memory lifetime. Generally, to apply such advanced aging-aware wear-leveling techniques proposed in the literature, additional special hardware is introduced into the memory system to provide the necessary information about the cell age and thus enable aging-aware wear-leveling decisions. This paper proposes software-only aging-aware wear-leveling based on common CPU features and does not rely on any additional hardware support from the memory subsystem. Specifically, we exploit the memory management unit (MMU), performance counters, and interrupts to approximate the memory write counts as an aging indicator. Although the software-only approach may lead to slightly worse wear-leveling, it is applicable on commonly available hardware. We achieve page-level coarse-grained wear-leveling by approximating the current cell age through statistical sampling and performing physical memory remapping through the MMU. This method results in non-uniform memory usage patterns within a memory page. Hence, we further propose a fine-grained wear-leveling in the stack region of C / C++ compiled software. By applying both wear-leveling techniques, we achieve up to $78.43\%$ of the ideal memory lifetime, which is a lifetime improvement of more than a factor of $900$ compared to the lifetime without any wear-leveling.
Software-controlled heterogeneous memory systems have the potential to improve performance, efficiency, and cost tradeoffs in emerging systems. Delivering on this promise requires an efficient operating system (OS) mechanisms and policies for data management. Unfortunately, modern OSes do not support efficient tiering of data between heterogeneous memories. While this problem is known (and is being studied) for application-level data pages, the question of how best to tier OS kernel objects has largely been ignored. We show that careful kernel object management is vital to the performance of software-controlled tiered memory systems. We find that the state-of-the-art OS page management research leaves considerable performance on the table by overlooking how best to tier, migrate, and manage kernel objects like inodes, dentry caches, journal blocks, network socket buffers, etc., associated with the filesystem and networking stack. In response, we characterize hotness, reuse, and liveness properties of kernel objects to develop appropriate tiering/migration mechanisms and policies. We evaluate our proposal using a real-system emulation framework on large-scale workloads like RocksDB, Redis, Cassandra, and Spark and achieve 1.4X to 4X higher throughput compared to the prior art.
With the alarming rate of security advisories and privacy concerns on connected devices, there is an urgent need for strong isolation guarantees in resource-constrained devices that demand very lightweight solutions. However, the status quo is that Unix-like operating systems do not offer privilege separation inside a process. Lack of practical fine-grained compartmentalization inside a shared address space leads to private data leakage through applications' untrusted dependencies and compromised threads. To this end, we propose $μ$Tiles, a lightweight kernel abstraction and set of security primitives based on mutual distrust for intra-process privilege separation, memory protection, and secure multithreading. $μ$Tiles takes advantage of hardware support for virtual memory tagging (e.g., ARM memory domains) to achieve significant performance gain while eliminating various hardware limitations. Our results (based on OpenSSL, the Apache HTTP server, and LevelDB) show that $μ$Tiles is extremely lightweight (adds $\approx 10KB$ to kernel image) for IoT use cases. It adds negligible runtime overhead ($\approx 0.5\%-3.5\%$) and is easy to integrate with existing applications for providing strong privilege separation.
File system checking and recovery (C/R) tools play a pivotal role in increasing the reliability of storage software, identifying and correcting file system inconsistencies. However, with increasing disk capacity and data content, file system C/R tools notoriously suffer from long runtimes. We posit that current file system checkers fail to exploit CPU parallelism and high throughput offered by modern storage devices. To overcome these challenges, we propose pFSCK, a tool that redesigns C/R to enable fine-grained parallelism at the granularity of inodes without impacting the correctness of C/R's functionality. To accelerate C/R, pFSCK first employs data parallelism by identifying functional operations in each stage of the checker and isolating dependent operation and their shared data structures. However, fully isolating shared structures is infeasible, consequently requiring serialization that limits scalability. To reduce the impact of synchronization bottlenecks and exploit CPU parallelism, pFSCK designs pipeline parallelism allowing multiple stages of C/R to run simultaneously without impacting correctness. To realize efficient pipeline parallelism for different file system data configurations, pFSCK provides techniques for ordering updates to global data structures, efficient per-thread I/O cache management, and dynamic thread placement across different passes of a C/R. Finally, pFSCK designs a resource-aware scheduler aimed towards reducing the impact of C/R on other applications sharing CPUs and the file system. Evaluation of pFSCK shows more than 2.6x gains of e2fsck and more than 1.8x over XFS's checker that provides coarse-grained parallelism.
Cryptographic algorithm implementations are vulnerable to Cold Boot attacks, which consist in exploiting the persistence of RAM cells across reboots or power down cycles to read the memory contents and recover precious sensitive data. The principal defensive weapon against Cold Boot attacks is memory encryption. In this work we propose MemShield, a memory encryption framework for user space applications that exploits a GPU to safely store the master key and perform the encryption/decryption operations. We developed a prototype that is completely transparent to existing applications and does not require changes to the OS kernel. We discuss the design, the related works, the implementation, the security analysis, and the performances of MemShield.
Vilamb provides efficient asynchronous systemredundancy for direct access (DAX) non-volatile memory (NVM) storage. Production storage deployments often use system-redundancy in form of page checksums and cross-page parity. State-of-the-art solutions for maintaining system-redundancy for DAX NVM either incur a high performance overhead or require specialized hardware. The Vilamb user-space library maintains system-redundancy with low overhead by delaying and amortizing the system-redundancy updates over multiple data writes. As a result, Vilamb provides 3--5x the throughput of the state-of-the-art software solution at high operation rates. For applications that need system-redundancy with high performance, and can tolerate some delaying of data redundancy, Vilamb provides a tunable knob between performance and quicker redundancy. Even with the delayed coverage, Vilamb increases the mean time to data loss due to firmware-induced corruptions by up to two orders of magnitude in comparison to maintaining no system-redundancy.
Tracing the sequence of library and system calls that a program makes is very helpful in the characterization of its interactions with the surrounding environment and ultimately of its semantics. Due to entanglements of real-world software stacks, accomplishing this task can be surprisingly challenging as we take accuracy, reliability, and transparency into the equation. To manage these dimensions effectively, we identify six challenges that API monitoring solutions should overcome and outline actionable design points for them, reporting insights from our experience in building API tracers for software security research. We detail two implementation variants, based on hardware-assisted virtualization (realizing the first general-purpose user-space tracer of this kind) and on dynamic binary translation, that achieve API monitoring robustly. We share our SNIPER system as open source.
Due to thermal and power supply limits, modern Intel CPUs reduce their frequency when AVX2 and AVX-512 instructions are executed. As the CPUs wait for 670μs before increasing the frequency again, the performance of some heterogeneous workloads is reduced. In this paper, we describe parallels between this situation and dynamic power management as well as between the policy implemented by these CPUs and fixed-timeout device shutdown policies. We show that the policy implemented by Intel CPUs is not optimal and describe potential better policies. In particular, we present a mechanism to classify applications based on their likeliness to cause frequency reduction. Our approach takes either the resulting classification information or information provided by the application and generates hints for the DVFS policy. We show that faster frequency changes based on these hints are able to improve performance for a web server using the OpenSSL library.
Diagnosing storage system failures is challenging even for professionals. One example is the "When Solid State Drives Are Not That Solid" incident occurred at Algolia data center, where Samsung SSDs were mistakenly blamed for failures caused by a Linux kernel bug. With the system complexity keeps increasing, such obscure failures will likely occur more often. As one step to address the challenge, we present our on-going efforts called X-Ray. Different from traditional methods that focus on either the software or the hardware, X-Ray leverages virtualization to collects events across layers, and correlates them to generate a correlation tree. Moreover, by applying simple rules, X-Ray can highlight critical nodes automatically. Preliminary results based on 5 failure cases shows that X-Ray can effectively narrow down the search space for failures.
High development velocity is critical for modern systems. This is especially true for Linux file systems which are seeing increased pressure from new storage devices and new demands on storage systems. However, high velocity Linux kernel development is challenging due to the ease of introducing bugs, the difficulty of testing and debugging, and the lack of support for redeployment without service disruption. Existing approaches to high-velocity development of file systems for Linux have major downsides, such as the high performance penalty for FUSE file systems, slowing the deployment cycle for new file system functionality. We propose Bento, a framework for high velocity development of Linux kernel file systems. It enables file systems written in safe Rust to be installed in the Linux kernel, with errors largely sandboxed to the file system. Bento file systems can be replaced with no disruption to running applications, allowing daily or weekly upgrades in a cloud server setting. Bento also supports userspace debugging. We implement a simple file system using Bento and show that it performs similarly to VFS-native ext4 on a variety of benchmarks and outperforms a FUSE version by 7x on 'git clone'. We also show that we can dynamically add file provenance tracking to a running kernel file system with only 15ms of service interruption.
Nowadays, in operating systems, numerous protection mechanisms prevent or limit the user-mode applicationsto access the kernels internal information. This is regularlycarried out by software-based defenses such as Address Space Layout Randomization (ASLR) and Kernel ASLR(KASLR). They play pronounced roles when the security of sandboxed applications such as Web-browser are considered.Armed with arbitrary write access in the kernel memory, if these protections are bypassed, an adversary could find a suitable where to write in order to get an elevation of privilege or code execution in ring 0. In this paper, we introduce a reliable method based on Transactional Synchronization Extensions (TSX) side-channel leakage to reveal the address of the Global Descriptor Table (GDT) and Interrupt Descriptor Table (IDT). We indicate that by detecting these addresses, one could execute instructions to sidestep the Intels User-Mode InstructionPrevention (UMIP) and the Hypervisor-based mitigation and, consequently, neutralized them. The introduced method is successfully performed after the most recent patches for Meltdown and Spectre. Moreover, the implementation of the proposed approach on different platforms, including the latest releases of Microsoft Windows, Linux, and, Mac OSX with the latest 9th generation of Intel processors, shows that the proposed mechanism is independent from the Operating System implementation. We demonstrate that a combinationof this method with call-gate mechanism (available in modernprocessors) in a chain of events will eventually lead toa system compromise despite the limitations of a super-secure sandboxed environment in the presence of Windows proprietary Virtualization Based Security (VBS). Finally, we suggest the software-based mitigation to avoid these issues with an acceptable overhead cost.
Robustness of a distributed computing system is defined as the ability to maintain its performance in the presence of uncertain parameters. Uncertainty is a key problem in heterogeneous (and even homogeneous) distributed computing systems that perturbs system robustness. Notably, the performance of these systems is perturbed by uncertainty in both task execution time and arrival. Accordingly, our goal is to make the system robust against these uncertainties. Considering task execution time as a random variable, we use probabilistic analysis to develop an autonomous proactive task dropping mechanism to attain our robustness goal. Specifically, we provide a mathematical model that identifies the optimality of a task dropping decision, so that the system robustness is maximized. Then, we leverage the mathematical model to develop a task dropping heuristic that achieves the system robustness within a feasible time complexity. Although the proposed model is generic and can be applied to any distributed system, we concentrate on heterogeneous computing (HC) systems that have a higher degree of exposure to uncertainty than homogeneous systems. Experimental results demonstrate that the autonomous proactive dropping mechanism can improve the system robustness by up to 20%.
Firecracker is a virtualization technology that makes use of Kernel Virtual Machine (KVM). Firecracker belongs to a new virtualization class named the micro-virtual machines (MicroVMs). Using Firecracker, we can launch lightweight MicroVMs in non-virtualized environments in a fraction of a second, at the same time offering the security and workload isolation provided by traditional VMs and also the resource efficiency that comes along with containers \cite{b1}. Firecracker aims to provide a slimmed-down MicroVM, comprised of approximately 50K lines of code in Rust and with a reduced attack surface for guest VMs. This report will examine the internals of Firecracker and understand why Firecracker is the next big thing going forward in virtualization and cloud computing.
The utilization of paging for virtual machine (VM) memory management is the root cause of memory virtualization overhead. This paper shows that paging is not necessary in the hypervisor. In fact, memory fragmentation, which explains paging utilization, is not an issue in virtualized datacenters thanks to VM memory demand patterns. Our solution Compromis, a novel Memory Management Unit, uses direct segment for VM memory management combined with paging for VM's processes. The paper presents a systematic methodology for implementing Compromis in the hardware, the hypervisor and the datacenter scheduler. Evaluation results show that Compromis outperforms the two popular memory virtualization solutions: shadow paging and Extended Page Table by up to 30% and 370% respectively.
Data centers are giant factories of Internet data and services. Worldwide data centers consume energy and emit emissions more than airline industry. Unfortunately, most of data centers are significantly underutilized. One of the major reasons is the big gaps between the real usage and the provisioned resources because users tend to over-estimate their demand and data center operators often rely on users' requests for resource allocation. In this paper, we first conduct an in-depth analysis of a Google cluster trace to unveil the root causes for low utilization and highlight the great potential to improve it. We then developed an online resource manager Flex to maximize the cluster utilization while satisfying the Quality of Service (QoS). Large-scale evaluations based on real-world traces show that Flex admits up to 1.74x more requests and 1.6x higher utilization compared to tradition schedulers while maintaining the QoS.
Cloud providers offer a variety of execution platforms in form of bare-metal, VM, and containers. However, due to the pros and cons of each execution platform, choosing the appropriate platform for a specific cloud-based application has become a challenge for solution architects. The possibility to combine these platforms (e.g. deploying containers within VMs) offers new capacities that makes the challenge even further complicated. However, there is a little study in the literature on the pros and cons of deploying different application types on various execution platforms. In particular, evaluation of diverse hardware configurations and different CPU provisioning methods, such as CPU pinning, have not been sufficiently studied in the literature. In this work, the performance overhead of container, VM, and bare-metal execution platforms are measured and analyzed for four categories of real-world applications, namely video processing, parallel processing (MPI), web processing, and No-SQL, respectively representing CPU intensive, parallel processing, and two IO intensive processes. Our analyses reveal a set of interesting and sometimes counterintuitive findings that can be used as best practices by the solution architects to efficiently deploy cloud-based applications. Here are some notable mentions: (A) Under specific circumstances, containers can impose a higher overhead than VMs; (B) Containers on top of VMs can mitigate the overhead of VMs for certain applications; (C) Containers with a large number of cores impose a lower overhead than those with a few cores.
Mutual exclusion (ME) is one of the most commonly used techniques to handle conflicts in concurrent systems. Traditionally, mutual exclusion algorithms have been designed under the assumption that a process does not fail while acquiring/releasing a lock or while executing its critical section. However, failures do occur in real life, potentially leaving the lock in an inconsistent state. This gives rise to the problem of \emph{recoverable mutual exclusion (RME)} that involves designing a mutual exclusion algorithm that can tolerate failures, while maintaining safety and liveness properties. One of the important measures of performance of any ME algorithm, including an RME algorithm, is the number of \emph{remote memory references (RMRs)} made by a process (for acquiring and releasing a lock as well as recovering the lock structure after a failure). The best known RME algorithm solves the problem for $n$ processes in sub-logarithmic number of RMRs, given by $\mathcal{O}(\frac{\log n}{\log \log n})$, irrespective of the number of failures in the system. In this work, we present a new algorithm for solving the RME problem whose RMR complexity gradually \emph{adapts} to the number of failures that have occurred in the system "recently". In the absence of failures, our algorithm generates only $\mathcal{O}(1)$ RMRs. Furthermore, its RMR complexity is given by $\mathcal{O}(\min\{ \sqrt{F}, \frac{\log n}{\log \log n} \})$ where $F$ is the total number of failures in the "recent" past. In addition to read and write instructions, our algorithm uses compare-and-swap (\CAS{}) and fetch-and-store (\FAS{}) hardware instructions, both of which are commonly available in most modern processors.