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 829 records · Page 46Linked to original sources

arXiv2025

Who is in Charge here? Understanding How Runtime Configuration Affects Software along with Variables&Constants

Runtime misconfiguration can lead to software performance degradation and even cause failure. Developers typically perform sanity checks during the configuration parsing stage to prevent invalid parameter values. However, we discovered that even valid values that pass these checks can also lead to unexpected severe consequences. Our study reveals the underlying reason: the value of runtime configuration parameters may interact with other constants and variables when propagated and used, altering its original effect on software behavior. Consequently, parameter values may no longer be valid when encountering complex runtime environments and workloads. Therefore, it is extremely challenging for users to properly configure the software before it starts running. This paper presents the first comprehensive and in-depth study (to the best of our knowledge) on how configuration affects software at runtime through the interaction with constants, and variables (PCV Interaction). Parameter values represent user intentions, constants embody developer knowledge, and variables are typically defined by the runtime environment and workload. This interaction essentially illustrates how different roles jointly determine software behavior. In this regard, we studied 705 configuration parameters from 10 large-scale software systems. We reveal that a large portion of configuration parameters interact with constants/variables after parsing. We analyzed the interaction patterns and their effects on software runtime behavior. Furthermore, we highlighted the risks of PCV interaction and identified potential issues behind specific interaction patterns. Our findings expose the "double edge" of PCV interaction, providing new insights and motivating the development of new automated techniques to help users configure software appropriately and assist developers in designing better configurations.

cs.SE↗

arXiv2025

HeteroPod: XPU-Accelerated Infrastructure Offloading for Commodity Cloud-Native Applications

Cloud-native systems increasingly rely on infrastructure services (e.g., service meshes, monitoring agents), which compete for resources with user applications, degrading performance and scalability. We propose HeteroPod, a new abstraction that offloads these services to Data Processing Units (DPUs) to enforce strict isolation while reducing host resource contention and operational costs. To realize HeteroPod, we introduce HeteroNet, a cross-PU (XPU) network system featuring: (1) split network namespace, a unified network abstraction for processes spanning CPU and DPU, and (2) elastic and efficient XPU networking, a communication mechanism achieving shared-memory performance without pinned resource overhead and polling costs. By leveraging HeteroNet and the compositional nature of cloud-native workloads, HeteroPod can optimally offload infrastructure containers to DPUs. We implement HeteroNet based on Linux, and implement a cloud-native system called HeteroK8s based on Kubernetes. We evaluate the systems using NVIDIA Bluefield-2 DPUs and CXL-based DPUs (simulated with real CXL memory devices). The results show that HeteroK8s effectively supports complex (unmodified) commodity cloud-native applications (up to 1 million LoC) and provides up to 31.9x better latency and 64x less resource consumption (compared with kernel-bypass design), 60% better end-to-end latency, and 55% higher scalability compared with SOTA systems.

cs.OS↗

arXiv2025

Extending Data Spatial Semantics for Scale Agnostic Programming

We introduce extensions to Data Spatial Programming (DSP) that enable scale-agnostic programming for application development. Building on DSP's paradigm shift from data-to-compute to compute-to-data, we formalize additional intrinsic language constructs that abstract persistent state, multi-user contexts, multiple entry points, and cross-machine distribution for applications. By introducing a globally accessible root node and treating walkers as potential entry points, we demonstrate how programs can be written once and executed across scales, from single-user to multi-user, from local to distributed, without modification. These extensions allow developers to focus on domain logic while delegating runtime concerns of persistence, multi-user support, distribution, and API interfacing to the execution environment. Our approach makes scale-agnostic programming a natural extension of the topological semantics of DSP, allowing applications to seamlessly transition from single-user to multi-user scenarios, from ephemeral to persistent execution contexts, and from local to distributed execution environments.

cs.PL↗

arXiv2025

Futureproof Static Memory Planning

The NP-complete combinatorial optimization task of assigning offsets to a set of buffers with known sizes and lifetimes so as to minimize total memory usage is called dynamic storage allocation (DSA). Existing DSA implementations bypass the theoretical state-of-the-art algorithms in favor of either fast but wasteful heuristics, or memory-efficient approaches that do not scale beyond one thousand buffers. The "AI memory wall", combined with deep neural networks' static architecture, has reignited interest in DSA. We present idealloc, a low-fragmentation, high-performance DSA implementation designed for million-buffer instances. Evaluated on a novel suite of particularly hard benchmarks from several domains, idealloc ranks first against four production implementations in terms of a joint effectiveness/robustness criterion.

cs.OS↗

arXiv2025

Zerrow: True Zero-Copy Arrow Pipelines in Bauplan

Bauplan is a FaaS-based lakehouse specifically built for data pipelines: its execution engine uses Apache Arrow for data passing between the nodes in the DAG. While Arrow is known as the "zero copy format", in practice, limited Linux kernel support for shared memory makes it difficult to avoid copying entirely. In this work, we introduce several new techniques to eliminate nearly all copying from pipelines: in particular, we implement a new kernel module that performs de-anonymization, thus eliminating a copy to intermediate data. We conclude by sharing our preliminary evaluation on different workloads types, as well as discussing our plan for future improvements.

cs.OS↗

arXiv2025

MigGPT: Harnessing Large Language Models for Automated Migration of Out-of-Tree Linux Kernel Patches Across Versions

Out-of-tree kernel patches are essential for adapting the Linux kernel to new hardware or enabling specific functionalities. Maintaining and updating these patches across different kernel versions demands significant effort from experienced engineers. Large language models (LLMs) have shown remarkable progress across various domains, suggesting their potential for automating out-of-tree kernel patch migration. However, our findings reveal that LLMs, while promising, struggle with incomplete code context understanding and inaccurate migration point identification. In this work, we propose MigGPT, a framework that employs a novel code fingerprint structure to retain code snippet information and incorporates three meticulously designed modules to improve the migration accuracy and efficiency of out-of-tree kernel patches. Furthermore, we establish a robust benchmark using real-world out-of-tree kernel patch projects to evaluate LLM capabilities. Evaluations show that MigGPT significantly outperforms the direct application of vanilla LLMs, achieving an average completion rate of 74.07 for migration tasks.

cs.SE↗

arXiv2025

Terminal Lucidity: Envisioning the Future of the Terminal

The Unix terminal, or just simply, the terminal, can be found being applied in almost every facet of computing. It is available across all major platforms and often integrated into other applications. Due to its ubiquity, even marginal improvements to the terminal have the potential to make massive improvements to productivity on a global scale. We believe that evolutionary improvements to the terminal, in its current incarnation as windowed terminal emulator, are possible and that developing a thorough understanding of issues that current terminal users face is fundamental to knowing how the terminal should evolve. In order to develop that understanding we have mined Unix and Linux Stack Exchange using a fully-reproducible method which was able to extract and categorize 91.0% of 1,489 terminal-related questions (from the full set of nearly 240,000 questions) without manual intervention. We present an analysis, to our knowledge the first of its kind, of windowed terminal-related questions posted over a 15-year period and viewed, in aggregate, approximately 40 million times. As expected, given its longevity, we find the terminal's many features being applied across a wide variety of use cases. We find evidence that the terminal, as windowed terminal emulator, has neither fully adapted to its now current graphical environment nor completely untangled itself from features more suited to incarnations in previous environments. We also find evidence of areas where we believe the terminal could be extended along with other areas where it could be simplified. Surprisingly, while many current efforts to improve the terminal include improving the terminal's social and collaborative aspects, we find little evidence of this as a prominent pain point.

cs.HC↗

arXiv2026

Towards High-Goodput LLM Serving with Prefill-decode Multiplexing

Large Language Model (LLM) serving must meet stringent Service Level Objectives (SLOs) for both the prefill and decode phases. Some existing solutions disaggregate the two phases, causing potential resource idleness or compute redundancy. Others split the prefill phase into chunks and fuse it with decode iteration, creating a dilemma between SLO compliance and high utilization. To address these issues, an efficient serving system should dynamically adapt compute allocation, decouple compute from memory management, and execute prefill and decode independently. We present MuxWise, an LLM serving framework that adopts a new paradigm, intra-GPU prefill-decode multiplexing, to meet these requirements. To fully exploit the paradigm, MuxWise integrates a bubble-less multiplex engine, a contention-tolerant estimator, and an SLO-aware dispatcher. Evaluation shows that MuxWise improves peak throughput under SLO guarantees by an average of 2.20x (up to 3.06x) over state-of-the-art baselines.

cs.OS↗

arXiv2025

UFO2: The Desktop AgentOS

Recent Computer-Using Agents (CUAs), powered by multimodal large language models (LLMs), offer a promising direction for automating complex desktop workflows through natural language. However, most existing CUAs remain conceptual prototypes, hindered by shallow OS integration, fragile screenshot-based interaction, and disruptive execution. We present UFO2, a multiagent AgentOS for Windows desktops that elevates CUAs into practical, system-level automation. UFO2 features a centralized HostAgent for task decomposition and coordination, alongside a collection of application-specialized AppAgent equipped with native APIs, domain-specific knowledge, and a unified GUI--API action layer. This architecture enables robust task execution while preserving modularity and extensibility. A hybrid control detection pipeline fuses Windows UI Automation (UIA) with vision-based parsing to support diverse interface styles. Runtime efficiency is further enhanced through speculative multi-action planning, reducing per-step LLM overhead. Finally, a Picture-in-Picture (PiP) interface enables automation within an isolated virtual desktop, allowing agents and users to operate concurrently without interference. We evaluate UFO2 across over 20 real-world Windows applications, demonstrating substantial improvements in robustness and execution accuracy over prior CUAs. Our results show that deep OS integration unlocks a scalable path toward reliable, user-aligned desktop automation.

cs.AI↗

arXiv2025

RAGDoll: Efficient Offloading-based Online RAG System on a Single GPU

Retrieval-Augmented Generation (RAG) enhances large language model (LLM) generation quality by incorporating relevant external knowledge. However, deploying RAG on consumer-grade platforms is challenging due to limited memory and the increasing scale of both models and knowledge bases. In this work, we introduce RAGDoll, a resource-efficient, self-adaptive RAG serving system integrated with LLMs, specifically designed for resource-constrained platforms. RAGDoll exploits the insight that RAG retrieval and LLM generation impose different computational and memory demands, which in a traditional serial workflow result in substantial idle times and poor resource utilization. Based on this insight, RAGDoll decouples retrieval and generation into parallel pipelines, incorporating joint memory placement and dynamic batch scheduling strategies to optimize resource usage across diverse hardware devices and workloads. Extensive experiments demonstrate that RAGDoll adapts effectively to various hardware configurations and LLM scales, achieving up to 3.6 times speedup in average latency compared to serial RAG systems based on vLLM.

cs.DC↗

arXiv2025

LithOS: An Operating System for Efficient Machine Learning on GPUs

The surging demand for GPUs in datacenters for machine learning (ML) has made efficient GPU utilization crucial. However, meeting the diverse needs of ML models while optimizing resource usage is challenging. To enable transparent, fine-grained GPU management that maximizes utilization and energy efficiency while maintaining strong isolation, an operating system (OS) approach is needed. This paper introduces LithOS, a first step toward a GPU OS. LithOS includes the following new abstractions and mechanisms for efficient GPU resource management: (i) a novel TPC Scheduler that supports spatial scheduling at the granularity of individual TPCs, unlocking efficient TPC stealing between workloads; (ii) transparent kernel atomization to reduce head-of-line blocking and enable dynamic resource reallocation mid-execution; (iii) a lightweight hardware right-sizing mechanism that determines the minimal TPC resources needed per atom; and (iv) a transparent power management mechanism that reduces power consumption based on in-flight work behavior. We implement LithOS in Rust and evaluate its performance across extensive ML environments, comparing it to state-of-the-art solutions from NVIDIA and prior research. For inference stacking, LithOS reduces tail latencies by 13x compared to MPS; compared to the best SotA, it reduces tail latencies by 3x while improving aggregate throughput by 1.6x. In hybrid inference-training stacking, LithOS reduces tail latencies by 4.7x compared to MPS; compared to the best SotA, it reduces tail latencies 1.18x while improving aggregate throughput by 1.35x. Finally, for a modest performance hit under 4%, LithOS's right-sizing provides a quarter of GPU capacity savings on average, while for a 7% hit, its power management yields a quarter of a GPU's energy savings. Overall, LithOS increases GPU efficiency, establishing a foundation for future OS research on GPUs.

cs.OS↗

arXiv2025

Guillotine: Hypervisors for Isolating Malicious AIs

As AI models become more embedded in critical sectors like finance, healthcare, and the military, their inscrutable behavior poses ever-greater risks to society. To mitigate this risk, we propose Guillotine, a hypervisor architecture for sandboxing powerful AI models -- models that, by accident or malice, can generate existential threats to humanity. Although Guillotine borrows some well-known virtualization techniques, Guillotine must also introduce fundamentally new isolation mechanisms to handle the unique threat model posed by existential-risk AIs. For example, a rogue AI may try to introspect upon hypervisor software or the underlying hardware substrate to enable later subversion of that control plane; thus, a Guillotine hypervisor requires careful co-design of the hypervisor software and the CPUs, RAM, NIC, and storage devices that support the hypervisor software, to thwart side channel leakage and more generally eliminate mechanisms for AI to exploit reflection-based vulnerabilities. Beyond such isolation at the software, network, and microarchitectural layers, a Guillotine hypervisor must also provide physical fail-safes more commonly associated with nuclear power plants, avionic platforms, and other types of mission critical systems. Physical fail-safes, e.g., involving electromechanical disconnection of network cables, or the flooding of a datacenter which holds a rogue AI, provide defense in depth if software, network, and microarchitectural isolation is compromised and a rogue AI must be temporarily shut down or permanently destroyed.

cs.CR↗

arXiv2025

Adaptive and Efficient Dynamic Memory Management for Hardware Enclaves

The second version of Intel Software Guard Extensions (Intel SGX), or SGX2, adds dynamic management of enclave memory and threads. The first version required the address space and thread counts to be fixed before execution. The Enclave Dynamic Memory Management (EDMM) feature of SGX2 has the potential to lower launch times and overall execution time. Despite reducing the enclave loading time by 28--93%, straightforward EDMM adoption strategies actually slow execution time down by as much as 58%. Using the Gramine library OS as a representative enclave runtime environment, this paper shows how to recover EDMM performance. The paper explains how implementing mutual distrust between the OS and enclave increases the cost of modifying page mappings. The paper then describes and evaluates a series of optimizations on application benchmarks, showing that these optimizations effectively eliminate the overheads of EDMM while retaining EDMM's performance and flexibility gains.

cs.OS↗

arXiv2025

Biting the CHERI bullet: Blockers, Enablers and Security Implications of CHERI in Defence

There is growing interest in securing the hardware foundations software stacks build upon. However, before making any investment decision, software and hardware supply chain stakeholders require evidence from realistic, multiple long-term studies of adoption. We present results from a 12 month evaluation of one such secure hardware solution, CHERI, where 15 teams from industry and academia ported software relevant to Defence to Arm's experimental Morello board. We identified six types of blocker inhibiting adoption: dependencies, a knowledge premium, missing utilities, performance, platform instability, and technical debt. We also identified three types of enabler: tool assistance, improved quality, and trivial code porting. Finally, we identified five types of potential vulnerability that CHERI could, if not appropriately configured, expand a system's attack surface: state leaks, memory leaks, use after free vulnerabilities, unsafe defaults, and tool chain instability. Future work should remove potentially insecure defaults from CHERI tooling, and develop a CHERI body of knowledge to further adoption.

cs.CR↗

arXiv2025

From Good to Great: Improving Memory Tiering Performance Through Parameter Tuning

Memory tiering systems achieve memory scaling by adding multiple tiers of memory wherein different tiers have different access latencies and bandwidth. For maximum performance, frequently accessed (hot) data must be placed close to the host in faster tiers and infrequently accessed (cold) data can be placed in farther slower memory tiers. Existing tiering solutions employ heuristics and pre-configured thresholds to make data placement and migration decisions. Unfortunately, these systems fail to adapt to different workloads and the underlying hardware, so perform sub-optimally. In this paper, we improve performance of memory tiering by using application behavior knowledge to set various parameters (knobs) in existing tiering systems. To do so, we leverage Bayesian Optimization to discover the good performing configurations that capture the application behavior and the underlying hardware characteristics. We find that Bayesian Optimization is able to learn workload behaviors and set the parameter values that result in good performance. We evaluate this approach with existing tiering systems, HeMem and HMSDK. Our evaluation reveals that configuring the parameter values correctly can improve performance by 2x over the same systems with default configurations and 1.56x over state-of-the-art tiering system.

cs.OS↗

arXiv2026

kAgent: An execution-guided crash resolution agent for the Linux kernel

Fuzzing frameworks like syzkaller have uncovered thousands of Linux kernel crashes, many of which are critical and security-sensitive. However, the ability to rapidly repair these crashes has not kept pace, particularly given the complexity and low-level nature of kernel code. Predominantly targeting user-space applications, existing LLM-based program repair techniques are not tailored to the unique challenges posed by kernel fuzz bugs-such as the absence of natural language bug reports, lack of exhaustive test oracles, and highly specialized crash artifacts. Thus, in this work, we first identify the prevalent bottlenecks that generic agents struggle with in complex systems such as the Linux kernel. Guided by these findings, we then build kAgent, a workflow-based agent inspired by how kernel developers diagnose and fix bugs, and kGym++, the co-designed toolstack supporting kAgent's requests. kAgent inspects relevant execution logs, generates execution-grounded natural language hypotheses, synthesizes candidate patches, validates patches through crash reproduction, and iteratively refines its reasoning. We ablate these agentic system features in kAgent and quantitatively analyze their contributions to the overall performance. We also report our experience on building agents for kernel crash repair. Although derived from this work on Linux, we note that our experience applies broadly to fuzzing-discovered bugs in complex systems software. We evaluate kAgent on kBenchSyz and show that it can repair up to 54.5% of crashes without localization and 65% with correct file hints. We also show kAgent's generalization on a few wild Syzkaller bugs, and how different patch types offer varying utility to developers who debug complex system software.

cs.SE↗

arXiv2025

OSVBench: Benchmarking LLMs on Specification Generation Tasks for Operating System Verification

We introduce OSVBench, a new benchmark for evaluating Large Language Models (LLMs) on the task of generating complete formal specifications for verifying the functional correctness of operating system kernels. This benchmark is built upon a real-world operating system kernel, Hyperkernel, and consists of 245 complex specification generation tasks in total, each of which is a long-context task of about 20k-30k tokens. The benchmark formulates the specification generation task as a program synthesis problem confined to a domain for specifying states and transitions. This formulation is provided to LLMs through a programming model. The LLMs must be able to understand the programming model and verification assumptions before delineating the correct search space for syntax and semantics and generating formal specifications. Guided by the operating system's high-level functional description, the LLMs are asked to generate a specification that fully describes all correct states and transitions for a potentially buggy code implementation of the operating system. Experimental results with 12 state-of-the-art LLMs indicate limited performance of existing LLMs on the specification generation task for operating system verification. Significant disparities in their performance highlight differences in their ability to handle long-context code generation tasks. The code are available at https://github.com/lishangyu-hkust/OSVBench

cs.CL↗

arXiv2026

Concurrency Testing in the Linux Kernel via eBPF

Concurrency is indispensable for modern software systems to meet performance and scalability demands, yet concurrency bugs remain notoriously difficult to detect and reproduce. Controlled Concurrency Testing (CCT) mitigates this challenge by systematically exploring thread interleavings through scheduling control. However, existing CCT approaches for OS kernels largely rely on external enforcement mechanisms, such as custom hypervisors or invasive kernel patches, resulting in substantial overhead and limited maintainability and extensibility. In this work, we present SECT, the first kernel-native concurrency fuzzing framework that rethinks scheduling as a first-class exploration mechanism. SECT introduces a novel CCT scheduler with temporal isolation scheduling and embeds programmable scheduling policies directly into the kernel dispatch path via eBPF, enabling fine-grained control over thread interleavings without customized hypervisors or extensive kernel core modification. In addition, SECT provides a preemption-safe instrumentation mechanism for injecting scheduling points at critical kernel events and incorporates a two-phase fuzzing workflow to jointly explore both sequential and concurrent behaviors. Our evaluation demonstrates that SECT achieves 38% more branches, 57% overhead reduction and 11.4$\times$ speed-up in bug exposure compared to a leading state-of-the-art kernel concurrency fuzzer. Moreover, SECT discovers eight previously unknown concurrency-related bugs in the Linux kernel, six of which have already been confirmed and fixed by developers.

cs.OS↗