Load Distribution: Implementation for the Mach Microkernel

1 Introduction.- 1.1 Motivation.- 1.2 Load Distribution.- 1.3 Research Contributions.- 1.4 Thesis Outline.- 2 Background and Related Work.- 2.1 Introduction.- 2.2 Migration.- 2.3 Load Information Management.- 2.4 Distributed Scheduling.- 2.5 Summary.- 3 Mach and Load Distribution.- 3.1 Introduction.- 3.2 Mach.- 3.3 Mach NORMA Version.- 3.4 Mach Support for Load Distribution.- 3.5 Load Distribution Architecture, Overview.- 3.6 Summary.- 4 Task Migration.- 4.1 Introduction.- 4.2 General Principles and Architecture.- 4.3 Requirements for Microkernels.- 4.4 Implementation.- 4.5 Performance Measurements.- 4.6 Related Work.- 4.7 Summary.- 5 Load Information Management.- 5.1 Introduction.- 5.2 Load Information Collection.- 5.3 Information Dissemination and Negotiation.- 5.4 Performance Measurements.- 5.5 Characterization of Mach Applications.- 5.6 Summary.- 6 Distributed Scheduling.- 6.1 Introduction.- 6.2 Distributed Scheduling Algorithms.- 6.3 Artificial Load.- 6.4 Performance Measurements.- 6.5 Summary.- 7 Lessons Learned.- 7.1 Introduction.- 7.2 Task Migration Implementation.- 7.3 Task Migration is not Always Enough.- 7.4 Task Migration v. Initial Placement.- 7.5 Microkernels are the Right Level for LD.- 7.6 Experiences with Network IPC.- 7.7 Fault Tolerance is Hard to Support.- 7.8 Summary.- 8 Conclusions and Future Work.- 8.1 Introduction.- 8.2 Summary of Results.- 8.3 Future Work.- 8.4 Conclusion.