Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 15 of 15 for “"Kernel Bypass"”.

  1. Exploring the Boundaries of Operating System in the Era of Ultra-fast Storage Technologies

    … storage hardware. Hence, the latency due user-kernel context switch caused by system calls and hardware interrupts is no longer negligible as presumed in the era of slower high latency hard disks. Further, the OS storage stack is not designed with multi-core scalability in mind; so with CPU …

    vt Repository record for Exploring the Boundaries of Operating System in the Era of Ultra-fast Storage Technologies (opens in a new tab)

  2. Fine-grained OS Control over High-performance Networking

    … hurdle in the usability of RDMA networks is kernel bypass, which removes the OS from the communication dataplane. While effective in High-Performance Computing, kernel bypass is problematic in cloud environments, where diverse applications rely on OS support for resource sharing. Removing …

    qucosa-diss

  3. Efficient, Secure, and Flexible High Speed Packet Processing for Data Centers

    … the network stack. Existing approaches such as kernel bypass and RDMA reduce software processing overhead but trade off policy compliance or flexibility for performance. This dissertation demonstrates data center packet processing can be made efficient, scalable, policy compliant, and flexible. …

    washington Repository record for Efficient, Secure, and Flexible High Speed Packet Processing for Data Centers (opens in a new tab)

  4. CO-DESIGNING SYSTEMS FOR MICROSECOND-SCALE CONSISTENT TAIL LATENCY IN DATACENTERS

    … balancing with TCP migration by co-designing a kernel-bypass network stack with programmable switches. Third, we present our ongoing work on an ML-native datapath OS architecture that leverages machine learning for adaptive runtime optimization. Collectively, this work demonstrates that …

    nus Repository record for CO-DESIGNING SYSTEMS FOR MICROSECOND-SCALE CONSISTENT TAIL LATENCY IN DATACENTERS (opens in a new tab) Download file for CO-DESIGNING SYSTEMS FOR MICROSECOND-SCALE CONSISTENT TAIL LATENCY IN DATACENTERS (opens in a new tab)

  5. TASNIC : a flexible TCP offload with programmable SmartNICs

    … packet processing is increasingly prohibitive. Kernel-bypass stacks and existing hardware offloads are not enough, causing operational issues at scale and cannot keep up with network protocol evolution. We take advantage of programmable SmartNICs to build TASNIC, a flexible, yet high-performance …

    texas Repository record for TASNIC : a flexible TCP offload with programmable SmartNICs (opens in a new tab)

  6. Designing Storage and Privacy-Preserving Systems for Large-Scale Cloud Applications

    … new design trends, such as in-memory storage, kernel-bypass message processing, and geo-distribution, have significantly improved the transaction processing times. However, they have also exposed overheads in the protocols used to implement these systems, which hinder their performance; …

    washington Repository record for Designing Storage and Privacy-Preserving Systems for Large-Scale Cloud Applications (opens in a new tab)

  7. UNiS: A User-space Non-intrusive Workflow-aware Virtual Network Function Scheduler

    … New packet processing models leveraging kernel bypass I/O and poll-mode processing have gained popularity for building high-performance VNFs because of their simple programming model and very low I/O overhead. However, a major drawback of such poll-mode processing is the inefficient use …

    waterloo Repository record for UNiS: A User-space Non-intrusive Workflow-aware Virtual Network Function Scheduler (opens in a new tab)

  8. Specializing a general-purpose operating system

    … from the operating system for high-speed I/O. Unikernels, library operating systems, and systems that exploit kernel bypass mechanisms have been developed to provide high-speed I/O by being specialized to meet the needs of performance-critical workloads. These systems have demonstrated immense …

    bu Repository record for Specializing a general-purpose operating system (opens in a new tab)

  9. Optimizing gem5 Simulator Performance: Profiling Insights and Userspace Networking Enhancements

    … networks are rapidly replacing the conventional kernel network stack. Nevertheless, the current state-of-the-art architectural simulator, gem5, still uses kernel networking which precludes realistic network application scenarios. First, we perform a comprehensive profiling study to identify and …

    ku Repository record for Optimizing gem5 Simulator Performance: Profiling Insights and Userspace Networking Enhancements (opens in a new tab)

  10. Addressing Design Trade-Offs for Practical Security Tools: Contributions to SGX I/O Performance and Directed Fuzzing Path Exploration

    … performance limitations of Intel SGX. Existing kernel-bypass solutions allow fast IO within enclaves but often expand the Trusted Computing Base (TCB), increase the attack surface, and complicate deployment. This work presents RAKIS, a system that enables enclave programs to securely access fast …

    gatech Repository record for Addressing Design Trade-Offs for Practical Security Tools: Contributions to SGX I/O Performance and Directed Fuzzing Path Exploration (opens in a new tab)

  11. Systems Support for Trusted Execution Environments

    … ShieldBox is our study of interplay of kernel bypass and trusted execution technologies for NFV, which also tackles the problem of low-latency clocks inside enclave. The two last systems, Clemmys and T-Lease are built on a more recent SGXv2 ISA extension. In Clemmys, SGXv2 allows us to …

    qucosa-diss

  12. Transparently accelerating IO-intensive applications

    As IO bandwidth continues to grow, processor speeds have stagnated. As such, the need to maximize the utility of our CPU cycles for IO-intensive applications is constantly growing. In my dissertation, I investigate processing bottlenecks for IO-intensive applications. I find that small and large IO …

    texas Repository record for Transparently accelerating IO-intensive applications (opens in a new tab)

  13. Accelerating Distributed Deep Learning via Software-Defined RDMA Transport in AI Data Centers

    … libraries such as NCCL and Gloo, providing kernel-bypass and zero-copy communication for high-throughput, low-latency data movement. However, existing RDMA transport designs have limitations for communication-intensive AI training in shared AI data center networks (DCNs). RDMA’s single-path …

    umn Repository record for Accelerating Distributed Deep Learning via Software-Defined RDMA Transport in AI Data Centers (opens in a new tab)

  14. Exploring high-level transport programming through eXpress Data Path

    … to implement transport protocols in the Linux Kernel. The Linux Kernel and its transport layer implementations are some of the most notable examples that highlight the challenges stated above. These implementations can require thousands of lines of code and hundreds of functions, which are …

    waterloo Repository record for Exploring high-level transport programming through eXpress Data Path (opens in a new tab)

  15. Characterizing and Modeling of Transport-Based Middleboxes

    … policies, that we implement in a high-speed kernel-bypass framework. Then, we rely on the latter to replicate existing path impairments, in a controlled environment, that we leverage to study how middleboxes affect TCP Quality-of-Service.

    liege Repository record for Characterizing and Modeling of Transport-Based Middleboxes (opens in a new tab)