C4.5: programs for machine learning
C4.5: programs for machine learning
User-level internet path diagnosis
SOSP '03 Proceedings of the nineteenth ACM symposium on Operating systems principles
STRIDER: A Black-box, State-based Approach to Change and Configuration Management and Support
LISA '03 Proceedings of the 17th USENIX conference on System administration
Semi-automated discovery of application session structure
Proceedings of the 6th ACM SIGCOMM conference on Internet measurement
Automated known problem diagnosis with event traces
Proceedings of the 1st ACM SIGOPS/EuroSys European Conference on Computer Systems 2006
On Inferring Application Protocol Behaviors in Encrypted Network Traffic
The Journal of Machine Learning Research
Improved error reporting for software that uses black-box components
Proceedings of the 2007 ACM SIGPLAN conference on Programming language design and implementation
Automatic misconfiguration troubleshooting with peerpressure
OSDI'04 Proceedings of the 6th conference on Symposium on Opearting Systems Design & Implementation - Volume 6
Effective diagnosis of routing disruptions from end systems
NSDI'08 Proceedings of the 5th USENIX Symposium on Networked Systems Design and Implementation
NetPrints: diagnosing home network misconfigurations using shared knowledge
NSDI'09 Proceedings of the 6th USENIX symposium on Networked systems design and implementation
Detailed diagnosis in enterprise networks
Proceedings of the ACM SIGCOMM 2009 conference on Data communication
DebugAdvisor: a recommender system for debugging
Proceedings of the the 7th joint meeting of the European software engineering conference and the ACM SIGSOFT symposium on The foundations of software engineering
Glasnost: enabling end users to detect traffic differentiation
NSDI'10 Proceedings of the 7th USENIX conference on Networked systems design and implementation
Netalyzr: illuminating the edge network
IMC '10 Proceedings of the 10th ACM SIGCOMM conference on Internet measurement
Toward the accurate identification of network applications
PAM'05 Proceedings of the 6th international conference on Passive and Active Network Measurement
Automated home network troubleshooting with device collaboration
Proceedings of the 2012 ACM conference on CoNEXT student workshop
Hi-index | 0.00 |
We ask the question: can network problems experienced by applications be identified based on symptoms contained in a network packet trace? An answer in the affirmative would open the doors to many opportunities, including non-intrusive monitoring of such problems on the network and matching a problem with past instances of the same problem. To this end, we present Deja vu, a tool to condense the manifestation of a network problem into a compact signature, which could then be used to match multiple instances of the same problem. Deja vu uses as input a network-level packet trace of an application's communication and extracts from it a set of features. During the training phase, each application run is manually labeled as GOOD or BAD, depending on whether the run was successful or not. Deja vu then employs a novel learning technique to build a signature tree not only to distinguish between GOOD and BAD runs but to also sub-classify the BAD runs, revealing the different classes of failures. The novelty lies in performing the sub-classification without requiring any failure class-specific labels. We evaluate Deja vu in the context of the multiple web browsers in a corporate environment and an email application in a university environment, with promising results. The signature generated by Deja vu based on the limited GOOD/BAD labels is as effective as one generated using full-blown classification with knowledge of the actual problem types.