BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//7.2.3.1//EN TZID:Asia/Kolkata X-WR-TIMEZONE:Asia/Kolkata BEGIN:VEVENT UID:87@cds.iisc.ac.in DTSTART;TZID=Asia/Kolkata:20241219T150000 DTEND;TZID=Asia/Kolkata:20241219T160000 DTSTAMP:20241205T073622Z URL:https://cds.iisc.ac.in/events/ph-d-thesis-defense-cds-december-19-2024 -application-service-resilience-in-cloud-an-end-to-end-perspective/ SUMMARY:Ph.D. Thesis Defense: CDS: December 19\, 2024 "Application Service Resilience In Cloud: An End-to-End Perspective" DESCRIPTION:DEPARTMENT OF COMPUTATIONAL AND DATA SCIENCES\n\nPh.D. Thesis D efense\n================================================================== ===\nSpeaker : Ms. Dhanya R Mathews\n\nS.R. Number : 06-18-02-10-12-18-1-1 5855\n\nTitle : "Application Service Resilience In Cloud: An End-to-End Pe rspective"\n\nResearch Supervisor: Dr. J. Lakshmi\n\nThesis examiner : Pro f. Praveen Tammana\, IIT-Hyderabad\n\nDate &\; Time : December 19\, 202 4 (Thursday) at 3:00 PM\n\nVenue : The Thesis Defense will be held on HYBR ID Mode\n\n# 102 CDS Seminar Hall /MICROSOFT TEAMS.\n\nPlease click on the following link to join the Thesis Defense\n\nMS Teams link\n============= ===========================================================\n\nABSTRACT\n\ nThe idea of computing as a utility was realized with the emergence of the cloud computing paradigm. Cloud service providers offer a wide range of s ervices that are delivered over the Internet to cloud service consumers. I n its current manifestation\, the Cloud services are realized over multipl e logical\, virtualized\, and distributed resources\, typically using a mu lti-layered architecture. The providers document the non-functional servic e level guarantees like availability\, performance\, security\, etc\, in S ervice Level Agreements (SLAs) provided to the consumer as Service Level O bjectives (SLO). The wide adoption of cloud computing\, compounded with th e emergence of microservice architecture\, has resulted in a considerable increase in the number of components involved in service delivery. Manuall y addressing failures in real-time is inefficient and often impossible at the cloud scale\, where failures are a norm rather than an exception. Ensu ring the quality of an application service\, as documented in the SLA\, th erefore requires autonomous mechanisms to enhance cloud services' resilien ce.\n\nThough cloud setups rely on highly autonomous service layers for ma naging\, provisioning\, and monitoring applications\, most of them focus o n a specific cloud service architecture layer or consider only a particula r set of faults. Any component across the cloud service stack involved in the service delivery could disrupt the SLO. Further\, as cloud services us e shared infrastructure\, monitoring and acting on the individual service layer metrics is limiting. In such a scenario\, the visibility of failure anywhere in the stack can offer effective recovery/remediation strategies\ ; hence\, an application-oriented approach that takes an end-to-end view o f failures makes a case for any resiliency solution. Towards this\, we pro pose an end-to-end service resilience framework that employs data-dependen t intelligent autonomous mechanisms to deal with cloud service disruptions efficiently. The intelligence to reduce the effect of disruptions is base d on understanding the complex interconnections and inter-dependencies of end-to-end components in the cloud service stack.\n\nThe different cloud s ervice abstraction layers and infrastructure sharing have resulted in incr eased occurrence of faults\, more specifically\, saturation faults. The in itial phase of this work examines real-world disruption scenarios to under stand the faults that could disrupt a cloud service. With ever-changing ap plications and environments on which they are hosted\, realizing a failure repository for cloud service faults is infeasible. This makes conventiona l data-oriented approaches less practical and dynamic observability data-o riented methods more desirable. Towards this\, the second phase of this wo rk developed a Topology Aware Root Cause Detection Algorithm (TA-RCD) that considers the observability data from end-to-end service components and t heir interconnectedness. Our results from the fault injection studies show that the proposed approach performs better than the state-of-the-art RCD algorithm\, at least by 2x times for Top-5 recall and 4x times for Top-3 r ecall\, on average.\n\nTo autonomously recover a service from its anomalou s state\, the remediation should target the root cause of anomalous behavi or. The root-cause localizations\, though accurate\, are not restricted to a specific component because of causal effects due to service interaction s. In order to identify the anomalous component\, the third phase of this work developed a Topology Aware end-to-end failure Recovery framework (TA- REC) that identifies the appropriate remediation strategy for an anomaly. The anomaly scores assignment and component activity tracking in TA-REC fa cilitates the identification of the component and the remediation that nee ds to be applied to the component. For the saturation fault scenarios inje cted across the stack\, TA-REC can identify an adequate remediation/recove ry strategy compared to the state-of-the-art because of the better visibil ity of the origin of the failure due to the end-to-end visibility.\n\nIn c onclusion\, this work demonstrated the usefulness of the end-to-end topolo gy of a cloud application service to remediate anomalies that challenge th e service quality efficiently. The observations prove that looking at the service as a black box restricts the development of intelligent autonomous approaches to guarantee SLOs. The proof-of-concept evaluations demonstrat ed that the intelligence to maintain service resilience effectively is bas ed on an accurate understanding of the end-to-end state\, as it facilitate s maintaining component serviceability by targeting the cause of failure i n the stack. Future work aims to evaluate both TA-RCD and TA-REC for a bro ader range of fault scenarios in real-life production deployments.\n\n==== =====================================================================\nALL ARE WELCOME CATEGORIES:Events,Thesis Defense END:VEVENT BEGIN:VTIMEZONE TZID:Asia/Kolkata X-LIC-LOCATION:Asia/Kolkata BEGIN:STANDARD DTSTART:20231220T150000 TZOFFSETFROM:+0530 TZOFFSETTO:+0530 TZNAME:IST END:STANDARD END:VTIMEZONE END:VCALENDAR