Kernel Threads Research Articles

Assessing the Cloud-RAN in the Linux Kernel: Sharing Computing and Network Resources.

Cloud-based Radio Access Network (Cloud-RAN) leverages virtualization to enable the coexistence of multiple virtual Base Band Units (vBBUs) with collocated workloads on a single edge computer, aiming for economic and operational efficiency. However, this coexistence can cause performance degradation in vBBUs due to resource contention. In this paper, we conduct an empirical analysis of vBBU performance on a Linux RT-Kernel, highlighting the impact of resource sharing with user-space tasks and Kernel threads. Furthermore, we evaluate CPU management strategies such as CPU affinity and CPU isolation as potential solutions to these performance challenges. Our results highlight that the implementation of CPU affinity can significantly reduce throughput variability by up to 40%, decrease vBBU's NACK ratios, and reduce vBBU scheduling latency within the Linux RT-Kernel. Collectively, these findings underscore the potential of CPU management strategies to enhance vBBU performance in Cloud-RAN environments, enabling more efficient and stable network operations. The paper concludes with a discussion on the efficient realization of Cloud-RAN, elucidating the benefits of implementing proposed CPU affinity allocations. The demonstrated enhancements, including reduced scheduling latency and improved end-to-end throughput, affirm the practicality and efficacy of the proposed strategies for optimizing Cloud-RAN deployments.

A Layered Mapping of Ada 202X to OpenMP

The OpenMP specification defines a set of compiler directives, library routines, and environment variables that together represent the OpenMP Application Programming Interface, and is currently defined for C, C++, and Fortran. The forthcoming version of Ada, currently dubbed Ada 202X, includes lightweight parallelism features, in particular parallel blocks and parallel loops. All versions of Ada, since its inception in 1983, have included "tasking," which corresponds to what are traditionally considered "heavyweight" parallelism features, or simply "concurrency" features. Ada "tasks" typically map to what are called "kernel threads," in that the operating system manages them and schedules them. However, one of the goals of lightweight parallelism is to reduce overhead by doing more of the management outside the kernel of the operating system, using a light-weight-thread (LWT) scheduler. The OpenMP library routines support both levels of threading, but for Ada 202X, the main interest is in making use of OpenMP for its lightweight thread scheduling capabilities.

GPU-Accelerated Self-Calibrating GRAPPA Operator Gridding for Rapid Reconstruction of Non-Cartesian MRI Data

Self-calibrating GRAPPA operator gridding (SC-GROG) is a method by which non-Cartesian (NC) data in magnetic resonance imaging (MRI) are shifted to the Cartesian k-space grid locations using the parallel imaging concept of GRAPPA operator. However, gridding with SC-GROG becomes computationally expensive and leads to longer reconstruction time when mapping a large number of NC samples in MRI data to the nearest Cartesian grid locations. This work aims to accelerate the SC-GROG for radial acquisitions in MRI, using massively parallel architecture of graphics processing units (GPUs). For this purpose, a novel implementation of GPU-accelerated SC-GROG is presented, which exploits the inherent parallelism in gridding operations. The proposed method employs the look-up-table (LUT)-based optimized kernels of compute unified device architecture (CUDA), to pre-calculate all the possible combinations of 2D-gridding weight sets and uses appropriate weight sets to shift the NC signals from multi-channel receiver coils at the nearest Cartesian grid locations. In the proposed method, LUTs are implemented to avoid the race condition among the CUDA kernel threads while shifting various NC points to the same Cartesian grid location. Several experiments using 24-channel simulated phantom and (12 and 30 channel) in vivo data sets are performed to evaluate the efficacy of the proposed method in terms of computation time and reconstruction accuracy. The results show that the GPU-based implementation of SC-GROG can significantly improve the image reconstruction efficiency, typically achieving 6× to 30× speed-up (including transfer time between CPU and GPU memory) without compromising the quality of image reconstruction.

Wait Analysis of Distributed Systems Using Kernel Tracing

We propose a new class of profiler for distributed and heterogeneous systems. In these systems, a task may wait for the result of another task, either locally or remotely. Such wait dependencies are invisible to instruction profilers. We propose a host-based, precise method to recover recursively wait causes across machines, using blocking as the fundamental mechanism to detect changes in the control flow. It relies solely on operating system events, namely scheduling, interrupts and network events. It is therefore capable of observing kernel threads interactions and achieves user-space runtime independence. Given a task, the algorithm computes its active path from the trace, which is presented in an interactive viewer for inspection. We validated our new method with workloads representing major architecture and operating conditions found in distributed programs. We then used our method to analyze the execution behavior of five different distributed systems. We found that the worst case tracing overhead for a distributed application is 18 percent and that the typical average overhead is about 5 percent. The analysis implementation has linear runtime according to the trace size.

Architectural Support for Handling Jitterin Shared Memory Based Parallel Applications

With an increasing number of cores per chip, it is becoming harder to guarantee optimal performance for parallel shared memory applications due to interference caused by kernel threads, interrupts, bus contention, and temperature management schemes (referred to as jitter). We demonstrate that the performance of parallel programs gets reduced (up to 35.22 percent) in large CMP based systems. In this paper, we characterize the jitter for large multi-core processors, and evaluate the loss in performance. We propose a novel jitter measurement unit that uses a distributed protocol to keep track of the number of wasted cycles. Subsequently, we try to compensate for jitter by using DVFS across a region of timing critical instructions called a frame. Additionally, we propose an OS cache that intelligently manages the OS cache lines to reduce memory interference. By performing detailed cycle accurate simulations, we show that we are able to execute a suite of Splash2 and Parsec benchmarks with a deterministic timing overhead limited to 2 percent for 14 out of 17 benchmarks with modest DVFS factors. We reduce the overall jitter by an average 13.5 percent for Splash2 and 6.4 percent for Parsec. The area overhead of our scheme is limited to 1 percent.

Preserving the original MPI semantics in a virtualized processor environment

Processor virtualization is a technique in which a programmer divides a computation into many entities, which are mapped to the available processors. The number of these entities, referred to as virtual processors, is typically larger than the number of physical processors. For an MPI program, the user decomposes the computation into more MPI tasks than physical processors. This approach allows overlapping computation and communication, and enables load balancing. User-level threads are often used to implement these virtual processors because they are generally faster to create, manage and migrate than heavy processes or kernel threads. However, these threads present issues concerning private data because they break the private address space assumption typically made by MPI programs. In this paper, we propose a new approach to privatize data in user-level threads. This approach is based on thread-local storage (TLS), which is often used by kernel threads. We apply this technique so that MPI programs can be executed in a virtualized environment while preserving their original semantics. We show that this alternative has a more efficient context switch and lower migration cost and is simpler to implement than other approaches.

Serialdriver: improving the reliability of device drivers through serialization

A great number of consumer electronic devices have emerged in recent years. To support these devices, many device drivers have been developed. These device drivers usually work in operating systems. Improper concurrency management causes lots of device driver bugs and the drivers' failures often lead to operating system crashes. Various approaches have been proposed to solve this problem, some of which use serialization to avoid the concurrency faults. However, these methods need to rewrite all the device drivers. This paper proposes SerialDriver, a new architecture to solve the concurrency faults of device drivers based on serialization. The proposed SerialDriver is composed of three components: an interface adapter, a message queue and a request processing thread. With the help of the interface adapter, SerialDriver gets rid of the need for reimplementing device drivers. In SerialDriver, requests from kernel threads to a device driver are placed in a message queue. The request processing thread of SerialDriver delivers these requests to the device driver sequentially. Extensive evaluation results show that SerialDriver serializes requests for a device driver successfully and the overhead incurred by SerialDriver is acceptable.

Kernel Thread Scheduling in Real-Time Linux for Wearable Computers

In Linux, real-time tasks are supported by separating real-time task priorities from non-real-time task priorities. However, this separation of priority ranges may not be effective when real-time tasks make the system calls that are taken care of by the kernel threads. Thus, Linux is considered a soft real-time system. Moreover, kernel threads are configured to have static priorities for throughputs. The static assignment of priorities to kernel threads causes trouble for real-time tasks when real-time tasks require kernel threads to be invoked to handle the system calls because kernel threads do not discriminate between real-time and non-real-time tasks. We present a dynamic kernel thread scheduling mechanism with weighted average priority inheritance protocol (PIP), a variation of the PIP. The scheduling algorithm assigns proper priorities to kernel threads at runtime by monitoring the activities of user-level real-time tasks. Experimental results show that the algorithms can greatly improve the unexpected execution latency of real-time tasks.

A thread-aware debugger with an open interface

While threads have become an accepted and standardized model for expressing concurrency and exploiting parallelism for the shared-memory model, debugging threads is still poorly supported. This paper identifies challenges in debugging threads and offers solutions to them. The contributions of this paper are threefold. First, an open interface for debugging as an extension to thread implementations is proposed. Second, extensions for thread-aware debugging are identified and implemented within the Gnu Debugger to provide additional features beyond the scope of existing debuggers. Third, an active debugging framework is proposed that includes a language-independent protocol to communicate between debugger and application via relational queries ensuring that the enhancements of the debugger are independent of actual thread implementations. Partial or complete implementations of the interface for debugging can be added to thread implementations to work in unison with the enhanced debugger without any modifications to the debugger itself. Sample implementations of the interface for debugging have shown its adequacy for user-level threads, kernel threads and mixed thread implementations while providing extended debugging functionality at improved efficiency and portability at the same time.

Composing high-performance schedulers: a case study from real-time simulation

Dynamic, high-performance or real-time applications require scheduling latencies and throughput not typically offered by current kernel or user-level threads schedulers. Moreover, it is widely accepted that it is important to be able to specialize scheduling policies for specific target applications and their execution environments. This paper presents one solution to the construction of such high-performance, application-specific thread schedulers. Specifically, scheduler implementations are composed from modular components, where individual scheduler modules may be specialized to underlying hardware characteristics or implement precisely the mechanisms and policies desired by application programs. The resulting user-level schedulers' implementations can provide resource guarantees by interaction with kernel-level facilities which provide means of resource reservation. This paper demonstrates the concept of composable schedulers by construction of several compositions for highly dynamic target applications, where low scheduling latencies are critical to application performance. Claims about the importance and effectiveness of scheduler composition are validated experimentally on a shared-memory multiprocessor. Scheduler compositions are optimized to take advantage of different low-level hardware attributes and of knowledge about application requirements specific to certain applications, including a Time Warp-based real-time discrete event simulator. Experimental evaluations are based on synthetic workloads, on a real-time simulation blending simulated with implemented control system components, and on a dynamic robot control program. Measurements indicate that schedulers can be composed and specialized to offer performance similar to that of dedicated scheduling co-processors. Copyright © 1999 John Wiley & Sons, Ltd.

Operating system support for distributed multimedia

We have been investigating an end system architecture to support networking with quality of service guarantees. For user level protocol code in our architecture to access the network, we have designed a kernel-user interface. The interface targets three areas for improvement: reduced copying, reduced reliance on explicit kernel-user interactions, and provision of rate-based flow control. In this paper, we present the concept of input-output efficient buffers for reduced copying, the concept of fast system calls for low-latency network access, and the concept of kernel threads for flow control. Also included is a concept called direct media streaming which is suitable for applications that require limited user processing of media data. These concepts have been implemented as an extension to SunOS 5.3 (the operating system component of Solaris 2.3). We report some experimental results on the performance of our current system.

Scheduler activations

Threadsare the vehicle for concurrency in many approaches to parallel programming. Threads can be supported either by the operating system kernel or by user-level library code in the application address space, but neither approach has been fully satisfactory.This paper addresses this dilemma. First, we argue that the performance of kernel threads isinherentlyworse than that of user-level threads, rather than this being an artifact of existing implementations; managing parallelism at the user level is essential to high-performance parallel computing. Next, we argue that the problems encountered in integrating user-level threads with other system services is a consequence of the lack of kernel support for user-level threads provided by contemporary multiprocessor operating systems; kernel threads are thewrong abstractionon which to support user-level management of parallelism. Finally, we describe the design, implementation, and performance of a new kernel interface and user-level thread package that together provide the same functionality as kernel threads without compromising the performance and flexibility advantages of user-level management of parallelism.

Scheduler activations

Threads are the vehicle for concurrency in many approaches to parallel programming. Threads separate the notion of a sequential execution stream from the other aspects of traditional UNIX-like processes, such as address spaces and I/O descriptors. The objective of this separation is to make the expression and control of parallelism sufficiently cheap that the programmer or compiler can exploit even fine-grained parallelism with acceptable overhead.Threads can be supported either by the operating system kernel or by user-level library code in the application address space, but neither approach has been fully satisfactory. This paper addresses this dilemma. First, we argue that the performance of kernel threads is inherently worse than that of user-level threads, rather than this being an artifact of existing implementations; we thus argue that managing parallelism at the user level is essential to high-performance parallel computing. Next, we argue that the lack of system integration exhibited by user-level threads is a consequence of the lack of kernel support for user-level threads provided by contemporary multiprocessor operating systems; we thus argue that kernel threads or processes, as currently conceived, are the wrong abstraction on which to support user-level management of parallelism. Finally, we describe the design, implementation, and performance of a new kernel interface and user-level thread package that together provide the same functionality as kernel threads without compromising the performance and flexibility advantages of user-level management of parallelism.