arXiv subjects

Sacheendra Talluri

Publications and source records attributed to Sacheendra Talluri.

13 recordsLinked to original sources

arXiv2026

M3SA: Exploring Datacenter Performance and Climate-Impact with Multi- and Meta-Model Simulation and Analysis

Datacenters are vital to our digital society, but consume a considerable fraction of global electricity and demand is projected to increase. To improve their sustainability and performance, we envision that simulators will become primary decision-making tools. However, and unlike other fields focusing on key societal infrastructure such as waterworks and mass transit, datacenter simulators do not yet combine multiple independent models into their operation and thus suffer from issues associated with singular models, such as specialization, and lack of adaptability to operational phenomena. To address this challenge, we propose M3SA, a datacenter simulation and analysis framework that uses discrete-event simulation to predict, for each model, the impact on climate and performance under various realistic datacenter conditions, and then combines these predictions. We design an architecture for simulating multiple concurrent models (Multi-Model), a technique for integrating the results of multiple models into a Meta-Model, and a procedure for quantifying Meta-Model accuracy. Through experiments with an M3SA prototype, we show that (i) M3SA can reproduce and enhance peer-reviewed experiments; (ii) M3SA can predict operational phenomena (e.g., failures) of datacenters, running fundamentally different workload traces; (iii) M3SA enables various types of what-if and how-to analysis, such as how to configure CO2-aware migration over yearly energy-production patterns. M3SA has been integrated into the open-source simulator OpenDC and is available at: https://github.com/atlarge-research/opendc-m3sa.

cs.DC↗

arXiv2026

Leveraging LLMs for Structured Information Extraction and Analysis from Cloud Incident Reports (Work In Progress Paper)

Incident management is essential to maintain the reliability and availability of cloud computing services. Cloud vendors typically disclose incident reports to the public, summarizing the failures and recovery process to help minimize their impact. However, such reports are often lengthy and unstructured, making them difficult to understand, analyze, and use for long-term dependability improvements. The emergence of LLMs offers new opportunities to address this challenge, but how to achieve this is currently understudied. In this paper, we explore the use of cutting-edge LLMs to extract key information from unstructured cloud incident reports. First, we collect more than 3,000 incident reports from 3 leading cloud service providers (AWS, AZURE, and GCP), and manually annotate these collected samples. Then, we design and compare 6 prompt strategies to extract and classify different types of information. We consider 6~LLM models, including 3 lightweight and 3 state-of-the-art (SotA), and evaluate model accuracy, latency, and token cost across datasets, models, prompts, and extracted fields. Our study has uncovered the following key findings: (1) LLMs achieve high metadata extraction accuracy, $75\%\text{--}95\%$ depending on the dataset. (2) Few-shot prompting generally improves accuracy for meta-data fields except for classification, and has better (lower) latency due to shorter output-tokens but requires $1.5\text{--}2\times$ more input-tokens. (3) Lightweight models (e.g., Gemini~2.0, GPT~3.5) offer favorable trade-offs in accuracy, cost, and latency; SotA models yield higher accuracy at significantly greater cost and latency. Our study provides tools, methodologies, and insights for leveraging LLMs to accurately and efficiently extract incident-report information. The FAIR data and code are publicly available at https://github.com/atlarge-research/llm-cloud-incident-extraction.

cs.PF↗

arXiv2026

OpenDC-STEAM: Realistic Modeling and Systematic Exploration of Composable Techniques for Sustainable Datacenters

The need to reduce datacenter carbon footprint is urgent. While many sustainability techniques have been proposed, they are often evaluated in isolation, using limited setups or analytical models that overlook real-world dynamics and interactions between methods. This makes it challenging for researchers and operators to understand the effectiveness and trade-offs of combining such techniques. We design OpenDC-STEAM, an open-source customizable datacenter simulator, to investigate the individual and combined impact of sustainability techniques on datacenter operational and embodied carbon emissions, and their trade-off with performance. Using STEAM, we systematically explore three representative techniques - horizontal scaling, leveraging batteries, and temporal shifting - with diverse representative workloads, datacenter configurations, and carbon-intensity traces. Our analysis highlights that datacenter dynamics can influence their effectiveness and that combining strategies can significantly lower emissions, but introduces complex cost-emissions-performance trade-offs that STEAM can help navigate. STEAM supports the integration of new models and techniques, making it a foundation framework for holistic, quantitative, and reproducible research in sustainable computing. Following open-science principles, STEAM is available as FOSS: https://github.com/atlarge-research/OpenDC-STEAM.

cs.DC↗

arXiv2025

Cloud Uptime Archive: Open-Access Availability Data of Web, Cloud, and Gaming Services

Cloud services are critical to society. However, their reliability is poorly understood. Towards solving the problem, we propose a standard repository for cloud uptime data. We populate this repository with the data we collect containing failure reports from users and operators of cloud services, web services, and online games. The multiple vantage points help reduce bias from individual users and operators. We compare our new data to existing failure data from the Failure Trace Archive and the Google cluster trace. We analyze the MTBF and MTTR, time patterns, failure severity, user-reported symptoms, and operator-reported symptoms of failures in the data we collect. We observe that high-level user facing services fail less often than low-level infrastructure services, likely due to them using fault-tolerance techniques. We use simulation-based experiments to demonstrate the impact of different failure traces on the performance of checkpointing and retry mechanisms. We release the data, and the analysis and simulation tools, as open-source artifacts available at https://github.com/atlarge-research/cloud-uptime-archive .

cs.DC↗

arXiv2025

An Empirical Characterization of Outages and Incidents in Public Services for Large Language Models

People and businesses increasingly rely on public LLM services, such as ChatGPT, DALLE, and Claude. Understanding their outages, and particularly measuring their failure-recovery processes, is becoming a stringent problem. However, only limited studies exist in this emerging area. Addressing this problem, in this work we conduct an empirical characterization of outages and failure-recovery in public LLM services. We collect and prepare datasets for 8 commonly used LLM services across 3 major LLM providers, including market-leads OpenAI and Anthropic. We conduct a detailed analysis of failure recovery statistical properties, temporal patterns, co-occurrence, and the impact range of outage-causing incidents. We make over 10 observations, among which: (1) Failures in OpenAI's ChatGPT take longer to resolve but occur less frequently than those in Anthropic's Claude;(2) OpenAI and Anthropic service failures exhibit strong weekly and monthly periodicity; and (3) OpenAI services offer better failure-isolation than Anthropic services. Our research explains LLM failure characteristics and thus enables optimization in building and using LLM systems. FAIR data and code are publicly available on https://zenodo.org/records/14018219 and https://github.com/atlarge-research/llm-service-analysis.

cs.PF↗

arXiv2024

Generic and ML Workloads in an HPC Datacenter: Node Energy, Job Failures, and Node-Job Analysis

HPC datacenters offer a backbone to the modern digital society. Increasingly, they run Machine Learning (ML) jobs next to generic, compute-intensive workloads, supporting science, business, and other decision-making processes. However, understanding how ML jobs impact the operation of HPC datacenters, relative to generic jobs, remains desirable but understudied. In this work, we leverage long-term operational data, collected from a national-scale production HPC datacenter, and statistically compare how ML and generic jobs can impact the performance, failures, resource utilization, and energy consumption of HPC datacenters. Our study provides key insights, e.g., ML-related power usage causes GPU nodes to run into temperature limitations, median/mean runtime and failure rates are higher for ML jobs than for generic jobs, both ML and generic jobs exhibit highly variable arrival processes and resource demands, significant amounts of energy are spent on unsuccessfully terminating jobs, and concurrent jobs tend to terminate in the same state. We open-source our cleaned-up data traces on Zenodo (https://doi.org/10.5281/zenodo.13685426), and provide our analysis toolkit as software hosted on GitHub (https://github.com/atlarge-research/2024-icpads-hpc-workload-characterization). This study offers multiple benefits for data center administrators, who can improve operational efficiency, and for researchers, who can further improve system designs, scheduling techniques, etc.

cs.DC↗

arXiv2023

Characterizing User and Provider Reported Cloud Failures

Cloud computing is the backbone of the digital society. Digital banking, media, communication, gaming, and many others depend on cloud services. Unfortunately, cloud services may fail, leading to damaged services, unhappy users, and perhaps millions of dollars lost for companies. Understanding a cloud service failure requires a detailed report on why and how the service failed. Previous work studies how cloud services fail using logs published by cloud operators. However, information is lacking on how users perceive and experience cloud failures. Therefore, we collect and characterize the data for user-reported cloud failures from Down Detector for three cloud service providers over three years. We count and analyze time patterns in the user reports, and derive failures from those user reports and characterize their duration and interarrival time. We characterize provider-reported cloud failures and compare the results with the characterization of user-reported failures. The comparison reveals the information of how users perceive failures and how much of the failures are reported by cloud service providers. Overall, this work provides a characterization of user- and provider-reported cloud failures and compares them with each other.

cs.DC↗

arXiv2023

The OpenDC Microservice Simulator: Design, Implementation, and Experimentation

Microservices is an architectural style that structures an application as a collection of loosely coupled services, making it easy for developers to build and scale their applications. The microservices architecture approach differs from the traditional monolithic style of treating software development as a single entity. Microservice architecture is becoming more and more adapted. However, microservice systems can be complex due to dependencies between the microservices, resulting in unpredictable performance at a large scale. Simulation is a cheap and fast way to investigate the performance of microservices in more detail. This study aims to build a microservices simulator for evaluating and comparing microservices based applications. The microservices reference architecture is designed. The architecture is used as the basis for a simulator. The simulator implementation uses statistical models to generate the workload. The compelling features added to the simulator include concurrent execution of microservices, configurable request depth, three load-balancing policies and four request execution order policies. This paper contains two experiments to show the simulator usage. The first experiment covers request execution order policies at the microservice instance. The second experiment compares load balancing policies across microservice instances.

cs.DC↗

arXiv2023

Failure Analysis of Big Cloud Service Providers Prior to and During Covid-19 Period

Cloud services are important for societal function such as healthcare, commerce, entertainment and education. Cloud can provide a variety of features such as increased collaboration and inexpensive computing. Failures are unavoidable in cloud services due to the large size and complexity, resulting in decreased reliability and efficiency. For example, due to bugs, many high-severity failures have been occurring in cloud infrastructure of popular providers, causing outages of several hours and the unrecoverable loss of user data. There are prior studies about cloud failure analyses are limited and use sources such as news articles. However, a detailed cloud failure focused study is required that provides analyses for cloud failure data gathered directly from the vendors. Furthermore, the Covid-19 cloud failures should be studied as cloud services played a major role throughout the Covid-19 period, as individuals relied on cloud services for activities such as working from home. A program can be made for this task. As a result, we will be able to better understand and mitigate cloud failures to reduce the effect of cloud failures.

cs.DC↗

arXiv2022

Let's Trace It: Fine-Grained Serverless Benchmarking using Synchronous and Asynchronous Orchestrated Applications

Making serverless computing widely applicable requires detailed performance understanding. Although contemporary benchmarking approaches exist, they report only coarse results, do not apply distributed tracing, do not consider asynchronous applications, and provide limited capabilities for (root cause) analysis. Addressing this gap, we design and implement ServiBench, a serverless benchmarking suite. ServiBench (i) leverages synchronous and asynchronous serverless applications representative of production usage, (ii) extrapolates cloud-provider data to generate realistic workloads, (iii) conducts comprehensive, end-to-end experiments to capture application-level performance, (iv) analyzes results using a novel approach based on (distributed) serverless tracing, and (v) supports comprehensively serverless performance analysis. With ServiBench, we conduct comprehensive experiments on AWS, covering five common performance factors: median latency, cold starts, tail latency, scalability, and dynamic workloads. We find that the median end-to-end latency of serverless applications is often dominated not by function computation but by external service calls, orchestration, or trigger-based coordination. We release collected experimental data under FAIR principles and ServiBench as a tested, extensible open-source tool.

cs.DC↗

arXiv2019

The Workflow Trace Archive: Open-Access Data from Public and Private Computing Infrastructures -- Technical Report

Realistic, relevant, and reproducible experiments often need input traces collected from real-world environments. We focus in this work on traces of workflows---common in datacenters, clouds, and HPC infrastructures. We show that the state-of-the-art in using workflow-traces raises important issues: (1) the use of realistic traces is infrequent, and (2) the use of realistic, {\it open-access} traces even more so. Alleviating these issues, we introduce the Workflow Trace Archive (WTA), an open-access archive of workflow traces from diverse computing infrastructures and tooling to parse, validate, and analyze traces. The WTA includes ${>}48$ million workflows captured from ${>}10$ computing infrastructures, representing a broad diversity of trace domains and characteristics. To emphasize the importance of trace diversity, we characterize the WTA contents and analyze in simulation the impact of trace diversity on experiment results. Our results indicate significant differences in characteristics, properties, and workflow structures between workload sources, domains, and fields.

cs.DC↗

arXiv2019

The AtLarge Vision on the Design of Distributed Systems and Ecosystems

High-quality designs of distributed systems and services are essential for our digital economy and society. Threatening to slow down the stream of working designs, we identify the mounting pressure of scale and complexity of \mbox{(eco-)systems}, of ill-defined and wicked problems, and of unclear processes, methods, and tools. We envision design itself as a core research topic in distributed systems, to understand and improve the science and practice of distributed (eco-)system design. Toward this vision, we propose the AtLarge design framework, accompanied by a set of 8 core design principles. We also propose 10 key challenges, which we hope the community can address in the following 5 years. In our experience so far, the proposed framework and principles are practical, and lead to pragmatic and innovative designs for large-scale distributed systems.

cs.DC↗

arXiv2018

Massivizing Computer Systems: a Vision to Understand, Design, and Engineer Computer Ecosystems through and beyond Modern Distributed Systems

Our society is digital: industry, science, governance, and individuals depend, often transparently, on the inter-operation of large numbers of distributed computer systems. Although the society takes them almost for granted, these computer ecosystems are not available for all, may not be affordable for long, and raise numerous other research challenges. Inspired by these challenges and by our experience with distributed computer systems, we envision Massivizing Computer Systems, a domain of computer science focusing on understanding, controlling, and evolving successfully such ecosystems. Beyond establishing and growing a body of knowledge about computer ecosystems and their constituent systems, the community in this domain should also aim to educate many about design and engineering for this domain, and all people about its principles. This is a call to the entire community: there is much to discover and achieve.

cs.DC↗