arXiv subjects

Sebastian Werner

Publications and source records attributed to Sebastian Werner.

27 records · Page 2Linked to original sources

arXiv2024

OXN -- Automated Observability Assessments for Cloud-Native Applications

Observability is important to ensure the reliability of microservice applications. These applications are often prone to failures, since they have many independent services deployed on heterogeneous environments. When employed "correctly", observability can help developers identify and troubleshoot faults quickly. However, instrumenting and configuring the observability of a microservice application is not trivial but tool-dependent and tied to costs. Practitioners need to understand observability-related trade-offs in order to weigh between different observability design alternatives. Still, these architectural design decisions are not supported by systematic methods and typically just rely on "professional intuition". To assess observability design trade-offs with concrete evidence, we advocate for conducting experiments that compare various design alternatives. Achieving a systematic and repeatable experiment process necessitates automation. We present a proof-of-concept implementation of an experiment tool - Observability eXperiment eNgine (OXN). OXN is able to inject arbitrary faults into an application, similar to Chaos Engineering, but also possesses the unique capability to modify the observability configuration, allowing for the straightforward assessment of design decisions that were previously left unexplored.

cs.SE↗

arXiv2024

Informed and Assessable Observability Design Decisions in Cloud-native Microservice Applications

Observability is important to ensure the reliability of microservice applications. These applications are often prone to failures, since they have many independent services deployed on heterogeneous environments. When employed "correctly", observability can help developers identify and troubleshoot faults quickly. However, instrumenting and configuring the observability of a microservice application is not trivial but tool-dependent and tied to costs. Architects need to understand observability-related trade-offs in order to weigh between different observability design alternatives. Still, these architectural design decisions are not supported by systematic methods and typically just rely on "professional intuition". In this paper, we argue for a systematic method to arrive at informed and continuously assessable observability design decisions. Specifically, we focus on fault observability of cloud-native microservice applications, and turn this into a testable and quantifiable property. Towards our goal, we first model the scale and scope of observability design decisions across the cloud-native stack. Then, we propose observability metrics which can be determined for any microservice application through so-called observability experiments. We present a proof-of-concept implementation of our experiment tool OXN. OXN is able to inject arbitrary faults into an application, similar to Chaos Engineering, but also possesses the unique capability to modify the observability configuration, allowing for the assessment of design decisions that were previously left unexplored. We demonstrate our approach using a popular open source microservice application and show the trade-offs involved in different observability design decisions.

cs.SE↗

arXiv2022

Hardless: A Generalized Serverless Compute Architecture for Hardware Processing Accelerators

The increasing use of hardware processing accelerators tailored for specific applications, such as the Vision Processing Unit (VPU) for image recognition, further increases developers' configuration, development, and management overhead. Developers have successfully used fully automated elastic cloud services such as serverless computing to counter these additional efforts and shorten development cycles for applications running on CPUs. Unfortunately, current cloud solutions do not yet provide these simplifications for applications that require hardware acceleration. However, as the development of specialized hardware acceleration continues to provide performance and cost improvements, it will become increasingly important to enable ease of use in the cloud. In this paper, we present an initial design and implementation of Hardless, an extensible and generalized serverless computing architecture that can support workloads for arbitrary hardware accelerators. We show how Hardless can scale across different commodity hardware accelerators and support a variety of workloads using the same execution and programming model common in serverless computing today.

cs.DC↗

arXiv2022

Synthesizing Configuration Tactics for Exercising Hidden Options in Serverless Systems

A proper configuration of an information system can ensure accuracy and efficiency, among other system objectives. Conversely, a poor configuration can have a significant negative impact on the system's performance, reliability, and cost. Serverless systems, which are comprised of many functions and managed services, especially risk exposure to misconfigurations, with many provider- and platform-specific, often intransparent and 'hidden' settings. In this paper, we argue to pay close attention to the configuration of serverless systems to exercise options with known accuracy, cost and time. Based on a literature study and long-term serverless systems development experience, we present nine tactics to unlock potentially neglected and unknown options in serverless systems.

cs.SE↗

arXiv2021

Application-Platform Co-Design for Serverless Data Processing

"Application-platform co-design" refers to the phenomenon of new platforms being created in response to changing application needs, followed by application design and development changing due to the emergence (and the specifics, limitations) of the new platforms, therefore creating, again, new application and platform requirements. This continuous process of application and platform (re-)design describes an engineering and management responsibility to constantly evaluate any given platform for application fit and platform-specific application design, and to consider a new or evolutionary platform development project due to evolving and changing application needs. In this paper, we study this phenomenon in the context of serverless computing and (big) data processing needs, and thus, for application-platform co-design for serverless data processing (SDP). We present an analysis of the state-of-the-art of function-as-a-service (FaaS) platforms, which reveals several configuration, deployment, execution, and measurement differences between popular platforms happening at-speed. These differences indicate already ongoing platform (re-)design processes resulting in more specialized serverless platforms and new, platform-specific challenges for application design. We discuss data processing needs of applications using the serverless model and present common initial (and undesirable) workaround solutions on the application level, giving additional argument to the creation of new SDP platforms. We present critical SDP requirements and possible new platform augmentations, but identify the need for engineering methods and tooling to better guide application-platform co-design. We argue to pay appropriate attention to the phenomenon of continuous application-platform co-design to better anticipate and to control future platform and application developments.

cs.SE↗

arXiv2021

FaaSter Troubleshooting -- Evaluating Distributed Tracing Approaches for Serverless Applications

Serverless applications can be particularly difficult to troubleshoot, as these applications are often composed of various managed and partly managed services. Faults are often unpredictable and can occur at multiple points, even in simple compositions. Each additional function or service in a serverless composition introduces a new possible fault source and a new layer to obfuscate faults. Currently, serverless platforms offer only limited support for identifying runtime faults. Developers looking to observe their serverless compositions often have to rely on scattered logs and ambiguous error messages to pinpoint root causes. In this paper, we investigate the use of distributed tracing for improving the observability of faults in serverless applications. To this end, we first introduce a model for characterizing fault observability, then provide a prototypical tracing implementation - specifically, a developer-driven and a platform-supported tracing approach. We compare both approaches with our model, measure associated trade-offs (execution latency, resource utilization), and contribute new insights for troubleshooting serverless compositions.

cs.SE↗

arXiv2019

A new operation mode for depth-focused high-sensitivity ToF range finding

We introduce pulsed correlation time-of-flight (PC-ToF) sensing, a new operation mode for correlation time-of-flight range sensors that combines a sub-nanosecond laser pulse source with a rectangular demodulation at the sensor side. In contrast to previous work, our proposed measurement scheme attempts not to optimize depth accuracy over the full measurement: With PC-ToF we trade the global sensitivity of a standard C-ToF setup for measurements with strongly localized high sensitivity -- we greatly enhance the depth resolution for the acquisition of scene features around a desired depth of interest. Using real-world experiments, we show that our technique is capable of achieving depth resolutions down to 2mm using a modulation frequency as low as 10MHz and an optical power as low as 1mW. This makes PC-ToF especially viable for low-power applications.

eess.IV↗

arXiv2017

Project Beehive: A Hardware/Software Co-designed Stack for Runtime and Architectural Research

The end of Dennard scaling combined with stagnation in architectural and compiler optimizations makes it challenging to achieve significant performance deltas. Solutions based solely in hardware or software are no longer sufficient to maintain the pace of improvements seen during the past few decades. In hardware, the end of single-core scaling resulted in the proliferation of multi-core system architectures, however this has forced complex parallel programming techniques into the mainstream. To further exploit physical resources, systems are becoming increasingly heterogeneous with specialized computing elements and accelerators. Programming across a range of disparate architectures requires a new level of abstraction that programming languages will have to adapt to. In software, emerging complex applications, from domains such as Big Data and computer vision, run on multi-layered software stacks targeting hardware with a variety of constraints and resources. Hence, optimizing for the power-performance (and resiliency) space requires experimentation platforms that offer quick and easy prototyping of hardware/software co-designed techniques. To that end, we present Project Beehive: A Hardware/Software co-designed stack for runtime and architectural research. Project Beehive utilizes various state-of-the-art software and hardware components along with novel and extensible co-design techniques. The objective of Project Beehive is to provide a modern platform for experimentation on emerging applications, programming languages, compilers, runtimes, and low-power heterogeneous many-core architectures in a full-system co-designed manner.

cs.DC↗

arXiv2017

Scratch iridescence: Wave-optical rendering of diffractive surface structure

The surface of metal, glass and plastic objects is often characterized by microscopic scratches caused by manufacturing and/or wear. A closer look onto such scratches reveals iridescent colors with a complex dependency on viewing and lighting conditions. The physics behind this phenomenon is well understood; it is caused by diffraction of the incident light by surface features on the order of the optical wavelength. Existing analytic models are able to reproduce spatially unresolved microstructure such as the iridescent appearance of compact disks and similar materials. Spatially resolved scratches, on the other hand, have proven elusive due to the highly complex wave-optical light transport simulations needed to account for their appearance. In this paper, we propose a wave-optical shading model based on non-paraxial scalar diffraction theory to render this class of effects. Our model expresses surface roughness as a collection of line segments. To shade a point on the surface, the individual diffraction patterns for contributing scratch segments are computed analytically and superimposed coherently. This provides natural transitions from localized glint-like iridescence to smooth BRDFs representing the superposition of many reflections at large viewing distances. We demonstrate that our model is capable of recreating the overall appearance as well as characteristic detail effects observed on real-world examples.

cs.GR↗