Kqueue - A Generic and Scalable Event Notification Facility
Proceedings of the FREENIX Track: 2001 USENIX Annual Technical Conference
The dawning of the autonomic computing era
IBM Systems Journal
Kernel korner: intro to inotify
Linux Journal
Autopilot: automatic data center management
ACM SIGOPS Operating Systems Review - Systems work at Microsoft Research
A scalable and explicit event delivery mechanism for UNIX
ATEC '99 Proceedings of the annual conference on USENIX Annual Technical Conference
PDA: a tool for automated problem determination
LISA'07 Proceedings of the 21st conference on Large Installation System Administration Conference
Portably solving file TOCTTOU races with hardness amplification
FAST'08 Proceedings of the 6th USENIX Conference on File and Storage Technologies
Extending futex for kernel to user notification
ACM SIGOPS Operating Systems Review - Research and developments in the Linux kernel
Guided Problem Diagnosis through Active Learning
ICAC '08 Proceedings of the 2008 International Conference on Autonomic Computing
The cost of a cloud: research problems in data center networks
ACM SIGCOMM Computer Communication Review
Future Generation Computer Systems
Fa: A System for Automating Failure Diagnosis
ICDE '09 Proceedings of the 2009 IEEE International Conference on Data Engineering
Evaluating the cost-benefit of using cloud computing to extend the capacity of clusters
Proceedings of the 18th ACM international symposium on High performance distributed computing
| Hi-index | 0.00 |
Cloud computing is becoming an important paradigm for information technology (IT) infrastructures. A key advantage of cloud computing is its ability to decrease the cost of computing for a variety of applications. For the infrastructure layer, which includes servers and operating systems (OSs), cost reduction is achieved through the consolidation of many OS instances onto a single physical server and through significant improvements in system-administrator productivity. However, these productivity improvements require a scalable easy-to-use OS event-management subsystem so that the higher level software can reliably and effectively automate operations. This paper presents the design and implementation of an OS event-monitoring subsystem called Autonomic Health Advisor FileSystem (AHAFS) that is scalable, has little system-performance overhead, and provides instantaneous event notifications with useful information, for improving the robustness, security, and performance of an OS instance. AHAFS is extensible and can monitor various events for a wide variety of event consumers. AHAFS does not require the use of a new application programming interface (API) but uses the ubiquitous filesystem API; hence, AHAFS is usable by monitoring applications written in any of the languages commonly used for monitoring (e.g., C, C++, Perl®, and Java®) without requiring additional runtime modules or packages.