Several recent proposals have shown that re-architecting the host network stack can significantly improve throughput and reduce tail latency. Yet these designs remain confined to user-level stacks or invasive kernel forks, both of which are impractical for production deployment.

Current memory tiering systems mitigate asymmetric latency through page migration between tiers. While this approach effectively hides latency, it overlooks scenarios where latency could potentially be tolerated. We propose that an efficient system should integrate both latency reduction (migration) and latency tolerance strategies. Our research demonstrates the effectiveness of prefetchers in tolerating latency within such systems, highlighting their importance in the design of high-performance memory tiering solutions.

Function-as-a-Service (FaaS) has emerged as a popular cloud paradigm that simplifies software development and deployment by providing scalable and event-driven function execution without the burden of managing servers.FaaS was originally created with a function as a function semantics to enable standalone microservices with adequately short execution time to meet microsecond-scale service-level objectives (SLOs).Unfortunately, today's FaaS systems fundamentally suffer from millisecond-level performance bottlenecks that arise from isolating functions in separate address spaces inside containers or microVMs.Prior work has focused on optimizing FaaS performance, but these systems still fall short of meeting microsecond-level SLOs.In this paper, we present Jord, a FaaS system that revives the original function-as-a-function vision of FaaS.Jord leverages hardware/software co-design to colocate functions in a single address space with user-level in-process memory isolation, extending the capability of traditional virtual memory.By performing memory isolation and management in nanoseconds, Jord enables zero-copy cross-function communication and scalable function dispatch, thereby minimizing FaaS overheads.We demonstrate that Jord can meet microsecond-level SLOs for microservice workloads while performing within 16% of an idealized but insecure baseline and delivering over 2× higher throughput compared to enhanced state-of-the-art systems.

Bugs in the Linux eBPF verifier may cause it to mistakenly accept unsafe eBPF programs or reject safe ones, causing either security or usability issues. While prior works on fuzzing the eBPF verifier have been effective, their bug oracles only hint at the existence of bugs indirectly (e.g., when a memory error occurs in downstream execution) instead of showing the root cause, confining them to uncover a narrow range of security bugs only with no detection of usability issues.

We analyze and enhance Trio and ArckFS by Zhou et al. (SOSP 2023), high-performance NVM file system architecture and file system. A group of authors from KAIST initiated this study through a careful review of the paper and the released artifact, seeking to enhance the Trio work. Their analysis identifies (1) insufficient clarity in the paper on the handling of multi-inode operations, and (2) several implementation bugs in ArckFS that cause occasional operation failures or potential crash inconsistencies during inode creation.

Performance-oriented applications require efficient locks to harness the computing power of multicore architectures. While fast, spinlock algorithms suffer severe performance degradation when thread counts exceed available hardware capacity, i.e., in oversubscribed scenarios. Existing solutions rely on imprecise heuristics for blocking, leading to suboptimal performance. We present FlexGuard, the first approach that systematically switches from busy-waiting to blocking precisely when a lock-holding thread is preempted. Flex-Guard achieves this by communicating with the OS scheduler via eBPF, unlike prior approaches. FlexGuard matches or improves performance in LevelDB, a memory-optimized database index, PARSEC's Dedup, and SPLASH2X's Raytrace and Streamcluster, boosting throughput by 1–6× in non-oversubscribed and up to 5× in oversubscribed scenarios.

Page-based far memory systems transparently expand an application's memory capacity beyond a single machine without modifying application code. However, existing systems are tailored to scenarios with low application thread counts, and fail to scale on today's multi-core machines. This makes them unsuitable for data-intensive applications that both rely on far memory support and scale with increasing thread count. Our analysis reveals that this poor scalability stems from inefficient holistic coordination between page fault-in and eviction operations. As thread count increases, current systems encounter scalability bottlenecks in TLB shootdowns, page accounting, and memory allocation.

This paper presents NFOS, a programming model, runtime, and profiler for productively developing software network functions (NFs) that scale on multicore machines. Writing shared-state concurrent systems that are both correct and scalable is still a serious challenge, which is why NFOS insulates developers from writing concurrent code.

We present ContextPrefetcher, a host-guided high-performant prefetching framework for near-storage accelerators that prefetches data blocks from storage (e.g., NAND) to device-level RAM. Efficiently prefetching data blocks to device-level RAM reduces storage access costs and improves I/O performance. We introduce a novel abstraction, Cross-layered Context (CLC), a virtual entity that spans across the host and the device and is used for identifying, managing, and tracking active and inactive data such as files, objects (within object stores), or a range of blocks. To support efficient prefetching of actively used CLCs to device memory without incurring near-device resource (memory and compute) bottlenecks, ContextPrefetcher delegates prefetching management to the host, guiding near-device compute to prefetch blocks of active CLC. Finally, ContextPrefetcher facilitates the swift reclamation of blocks associated with inactive CLC. Preliminary evaluation against state-of-the-art near-storage accelerator designs demonstrates performance gains of up to 1.34X.

The ability to safely extend OS kernel functionality is a longstanding goal in OS design, with the widespread use of the eBPF framework in Linux and Windows demonstrating the benefits of such extensibility. However, existing solutions for kernel extensibility (including eBPF) are limited and constrain users either in the extent of functionality that they can offload to the kernel or the performance overheads incurred by their extensions.

Data-intensive systems are the backbone of today's computing and are responsible for shaping data centers. Over the years, cloud providers have relied on three principles to maintain cost-effective data systems: use disaggregation to decouple scaling, use domain-specific computing to battle waning laws, and use serverless to lower costs. Although they work well individually, they fail to work in harmony: an issue amplified by emerging data system workloads.

Userspace library file systems (LibFSes) promise to unleash the performance potential of non-volatile memory (NVM) by directly accessing it and enabling unprivileged applications to customize their LibFSes to their workloads. Unfortunately, such benefits pose a significant challenge to ensuring metadata integrity. Existing works either underutilize NVM's performance or forgo critical file system security guarantees.

Disaggregated memory can address resource provisioning inefficiencies in current datacenters. Multiple software runtimes for disaggregated memory have been proposed in an attempt to make disaggregated memory practical. These systems rely on the virtual memory subsystem to transparently offer disaggregated memory to applications using a local memory abstraction. Unfortunately, using virtual memory for disaggregation has multiple limitations, including high overhead that comes from the use of page faults to identify what data to fetch and cache locally, and high dirty data amplification that comes from the use of page-granularity for tracking changes to the cached data (4KB or higher).

Kernel synchronization primitives are of paramount importance to achieving good performance and scalability for applications. However, they are usually invisible and out of the reach of application developers. Instead, kernel developers and synchronization experts make all the decisions regarding kernel lock design.

Non-Volatile Memory (NVM), which provides relatively fast and byte-addressable persistence, is now commercially available. However, we cannot equate a real NVM with a slow DRAM, as it is much more complicated than we expect. In this work, we revisit and analyze both NVM and NVM-specific persistent memory indexes. We find that there is still a lot of room for improvement if we consider NVM hardware, its software stack, persistent index design, and concurrency control. Based on our analysis, we propose Packed Asynchronous Concurrency (PAC) guidelines for designing high-performance persistent index structures. The key idea behind the guidelines is to 1) access NVM hardware in a packed manner to minimize its bandwidth utilization and 2) exploit asynchronous concurrency control to decouple the long NVM latency from the critical path of the index.

RDMA-capable networks are gaining traction with datacenter deployments due to their high throughput, low latency, CPU efficiency, and advanced features, such as remote memory operations. However, efficiently utilizing RDMA capability in a common setting of high fan-in, fan-out asymmetric network topology is challenging. For instance, using RDMA programming features comes at the cost of connection scalability, which does not scale with increasing cluster size. To address that, several works forgo some RDMA features by only focusing on conventional RPC APIs.

Data races occur when two threads fail to use proper synchronization when accessing shared data. In kernel file systems, which are highly concurrent by design, data races are common mistakes and often wreak havoc on the users, causing inconsistent states or data losses. Prior fuzzing practices on file systems have been effective in uncovering hundreds of bugs, but they mostly focus on the sequential aspect of file system execution and do not comprehensively explore the concurrency dimension and hence, forgo the opportunity to catch data races.In this paper, we bring coverage-guided fuzzing to the concurrency dimension with three new constructs: 1) a new coverage tracking metric, alias coverage, specially designed to capture the exploration progress in the concurrency dimension; 2) an evolution algorithm for generating, mutating, and merging multi-threaded syscall sequences as inputs for concurrency fuzzing; and 3) a comprehensive lockset and happens-before modeling for kernel synchronization primitives for precise data race detection. These components are integrated into Krace, an end-to-end fuzzing framework that has discovered 23 data races in ext4, btrfs, and the VFS layer so far, and 9 are confirmed to be harmful.

File systems are too large to be bug free. Although handwritten test suites have been widely used to stress file systems, they can hardly keep up with the rapid increase in file system size and complexity, leading to new bugs being introduced. These bugs come in various flavors: buffer overflows to complicated semantic bugs. Although bug-specific checkers exist, they generally lack a way to explore file system states thoroughly. More importantly, no turnkey solution exists that unifies the checking effort of various aspects of a file system under one umbrella. In this article, to highlight the potential of applying fuzzing to find any type of file system bugs in a generic way, we propose H ydra , an extensible fuzzing framework. H ydra provides building blocks for file system fuzzing, including input mutators, feedback engines, test executors, and bug post-processors. As a result, developers only need to focus on building the core logic for finding bugs of their interests. We showcase the effectiveness of H ydra with four checkers that hunt crash inconsistency, POSIX violations, logic assertion failures, and memory errors. So far, H ydra has discovered 157 new bugs in Linux file systems, including three in verified file systems (FSCQ and Yxv6).

This paper presents multi-version read-log-update (MV-RLU), an extension of the read-log-update (RLU) synchronization mechanism. While RLU has many merits including an intuitive programming model and excellent performance for read-mostly workloads, we observed that the performance of RLU significantly drops in workloads with more write operations. The core problem is that RLU manages only two versions. To overcome such limitation, we extend RLU to support multi-versioning and propose new techniques to make multi-versioning efficient. At the core of MV-RLU design is concurrent autonomous garbage collection, which prevents reclaiming invisible versions being a bottleneck, and reduces the version traversal overhead the main overhead of multi-version design. We extensively evaluate MV-RLU with the state-of-the-art synchronization mechanisms, including RCU, RLU, software transactional memory (STM), and lock-free approaches, on concurrent data structures and real-world applications (database concurrency control and in-memory key-value store). Our evaluation results show that MV-RLU significantly outperforms other techniques for a wide range of workloads with varying contention levels and data-set size.

We present SplitFS, a file system for persistent memory (PM) that reduces software overhead significantly compared to state-of-the-art PM file systems. SplitFS presents a novel split of responsibilities between a user-space library file system and an existing kernel PM file system. The user-space library file system handles data operations by intercepting POSIX calls, memory-mapping the underlying file, and serving the read and overwrites using processor loads and stores. Metadata operations are handled by the kernel PM file system (ext4 DAX). SplitFS introduces a new primitive termed relink to efficiently support file appends and atomic data operations. SplitFS provides three consistency modes, which different applications can choose from, without interfering with each other. SplitFS reduces software overhead by up-to 4x compared to the NOVA PM file system, and 17x compared to ext4 DAX. On a number of micro-benchmarks and applications such as the LevelDB key-value store running the YCSB benchmark, SplitFS increases application performance by up to 2x compared to ext4 DAX and NOVA while providing similar consistency guarantees.

Locks are an essential building block for high-performance multicore system software. To meet performance goals, lock algorithms have evolved towards specialized solutions for architectural characteristics (e.g., NUMA). However, inpractice, applications run on different server platforms and exhibit widely diverse behaviors that evolve with time (e.g., number of threads, number of locks). This creates performance and scalability problems for locks optimized for a single scenario and platform. For example, popular spinlocks suffer from excessive cache-line bouncing in NUMA systems, while scalable, NUMA-aware locks exhibit sub-par single-thread performance.

File systems are too large to be bug free. Although handwritten test suites have been widely used to stress file systems, they can hardly keep up with the rapid increase in file system size and complexity, leading to new bugs being introduced and reported regularly. These bugs come in various flavors: simple buffer overflows to sophisticated semantic bugs. Although bug-specific checkers exist, they generally lack a way to explore file system states thoroughly. More importantly, no turnkey solution exists that unifies the checking effort of various aspects of a file system under one umbrella.

We present Recipe, a principled approach for converting concurrent DRAM indexes into crash-consistent indexes for persistent memory (PM). The main insight behind Recipe is that isolation provided by a certain class of concurrent in-memory indexes can be translated with small changes to crash-consistency when the same index is used in PM. We present a set of conditions that enable the identification of this class of DRAM indexes, and the actions to be taken to convert each index to be persistent. Based on these conditions and conversion actions, we modify five different DRAM indexes based on B+ trees, tries, radix trees, and hash tables to their crash-consistent PM counterparts. The effort involved in this conversion is minimal, requiring 30--200 lines of code. We evaluated the converted PM indexes on Intel DC Persistent Memory, and found that they outperform state-of-the-art, hand-crafted PM indexes in multi-threaded workloads by up-to 5.2x. For example, we built P-CLHT, our PM implementation of the CLHT hash table by modifying only 30 LOC. When running YCSB workloads, P-CLHT performs up to 2.4x better than Cacheline-Conscious Extendible Hashing (CCEH), the state-of-the-art PM hash table.

File systems, a basic building block of an OS, are too big and too complex to be bug free. Nevertheless, file systems rely on regular stress-testing tools and formal checkers to find bugs, which are limited due to the ever-increasing complexity of both file systems and OSes. Thus, fuzzing, proven to be an effective and a practical approach, becomes a preferable choice, as it does not need much knowledge about a target. However, three main challenges exist in fuzzing file systems: mutating a large image blob that degrades overall performance, generating image-dependent file operations, and reproducing found bugs, which is difficult for existing OS fuzzers. Hence, we present JANUS, the first feedback-driven fuzzer that explores the two-dimensional input space of a file system, i.e., mutating metadata on a large image, while emitting image-directed file operations. In addition, JANUS relies on a library OS rather than on traditional VMs for fuzzing, which enables JANUS to load a fresh copy of the OS, thereby leading to better reproducibility of bugs. We evaluate JANUS on eight file systems and found 90 bugs in the upstream Linux kernel, 62 of which have been acknowledged. Forty-three bugs have been fixed with 32 CVEs assigned. In addition, JANUS achieves higher code coverage on all the file systems after fuzzing 12 hours, when compared with the state-of-the-art fuzzer Syzkaller for fuzzing file systems. JANUS visits 4.19x and 2.01x more code paths in Btrfs and ext4, respectively. Moreover, JANUS is able to reproduce 88-100% of the crashes, while Syzkaller fails on all of them.

We propose LATR-lazy TLB coherence-a software-based TLB shootdown mechanism that can alleviate the overhead of the synchronous TLB shootdown mechanism in existing operating systems. By handling the TLB coherence in a lazy fashion, LATR can avoid expensive IPIs which are required for delivering a shootdown signal to remote cores, and the performance overhead of associated interrupt handlers. Therefore, virtual memory operations, such as free and page migration operations, can benefit significantly from LATR's mechanism. For example, LATR improves the latency of munmap() by 70.8% on a 2-socket machine, a widely used configuration in modern data centers. Real-world, performance-critical applications such as web servers can also benefit from LATR: without any application-level changes, LATR improves Apache by 59.9% compared to Linux, and by 37.9% compared to ABIS, a highly optimized, state-of-the-art TLB coherence technique.

Timestamping is an essential building block for designing concurrency control mechanisms and concurrent data structures. Various algorithms either employ physical timestamping, assuming that they have access to synchronized clocks, or maintain a logical clock with the help of atomic instructions. Unfortunately, these approaches have two problems. First, hardware developers do not guarantee that the available hardware clocks are exactly synchronized, which they find difficult to achieve in practice. Second, the atomic instructions are a deterrent to scalability resulting from cache-line contention. This paper addresses these problems by proposing and designing a scalable ordering primitive, called Ordo, that relies on invariant hardware clocks. Ordo not only enables the correct use of these clocks, by providing a notion of a global hardware clock, but also frees various logical timestamp-based algorithms from the burden of the software logical clock, while trying to simplify their design. We use the Ordo primitive to redesign 1) a concurrent data structure library that we apply on the Linux kernel; 2) a synchronization mechanism for concurrent programming; 3) two database concurrency control mechanisms; and 4) a clock-based software transactional memory algorithm. Our evaluation shows that there is a possibility that the clocks are not synchronized on two architectures (Intel and ARM) and that Ordo generally improves the efficiency of several algorithms by 1.2--39.7X on various architectures.

We propose Solros---a new operating system architecture for heterogeneous systems that comprises fast host processors, slow but massively parallel co-processors, and fast I/O devices. A general consensus to fully drive such a hardware system is to have a tight integration among processors and I/O devices. Thus, in the Solros architecture, a co-processor OS (data-plane OS) delegates its services, specifically I/O stacks, to the host OS (control-plane OS). Our observation for such a design is that global coordination with system-wide knowledge (e.g., PCIe topology, a load of each co-processor) and the best use of heterogeneous processors is critical to achieving high performance. Hence, we fully harness these specialized processors by delegating complex I/O stacks on fast host processors, which leads to an efficient global coordination at the level of the control-plane OS.

Fuzzing is a software testing technique that finds bugs by repeatedly injecting mutated inputs to a target program. Known to be a highly practical approach, fuzzing is gaining more popularity than ever before. Current research on fuzzing has focused on producing an input that is more likely to trigger a vulnerability.

Processing a one trillion-edge graph has recently been demonstrated by distributed graph engines running on clusters of tens to hundreds of nodes. In this paper, we employ a single heterogeneous machine with fast storage media (e.g., NVMe SSD) and massively parallel coprocessors (e.g., Xeon Phi) to reach similar dimensions. By fully exploiting the heterogeneous devices, we design a new graph processing engine, named Mosaic, for a single machine. We propose a new locality-optimizing, space-efficient graph representation---Hilbert-ordered tiles, and a hybrid execution model that enables vertex-centric operations in fast host processors and edge-centric operations in massively parallel coprocessors.

Today, systems software is too complex to be bug-free. To find bugs in systems software, developers often rely on code checkers, like Linux's Sparse. However, the capability of existing tools used in commodity, large-scale systems is limited to finding only shallow bugs that tend to be introduced by simple programmer mistakes, and so do not require a deep understanding of code to find them. Unfortunately, the majority of bugs as well as those that are difficult to find are semantic ones, which violate high-level rules or invariants (e.g., missing a permission check). Thus, it is difficult for code checkers lacking the understanding of a programmer's true intention to reason about semantic correctness.

Today, IaaS cloud providers are dynamically minimizing the cost of data centers operations, while maintaining the Service Level Agreement (SLA). Currently, this is achieved by the live migration capability, which is an advanced state-of-the-art technology of Virtualization. However, existing migration techniques suffer from high network bandwidth utilization, large network data transfer, large migration time as well as the destination's VM failure during migration. In this paper, we propose Reliable Lazy Copy (RLC) - a fast, efficient and a reliable migration technique. RLC provides a reasonable solution for high-efficiency and less disruptive migration scheme by utilizing the three phases of the process migration. For effective network bandwidth utilization and reducing the total migration time, we introduce a learning phase to estimate the writable working set (WWS) prior to the migration, resulting in an almost single time transfer of the pages. Our approach decreases the total data transfer by 1.16 x - 12.21x and the total migration time by a factor of 1.42x - 9.84x against the existing approaches, thus providing a fast and an efficient, reliable VM migration of the VMs in the cloud.