Multilayer Virtualized Systems Analysis with Kernel Tracing

This paper studies interactions between virtual machines and their host through the sharing of resources like physical CPUs. We present an analysis based on kernel tracing that erases the bounds between virtual machines and their host to reduce the multilayer system into a single layer. For this analysis we developed a view that displays a time line for each host's CPU, showing across time which process is running, even if it is from a virtual machine. By using a system of filters, we added the possibility to highlight in this view either traced machines, virtual CPUs or specific processes. This last feature grants the possibility to precisely see on the host where and when a virtual machine's thread is running.

[1]  Michel Dagenais,et al.  Fine-grained preemption analysis for latency investigation across virtual machines , 2014, Journal of Cloud Computing.

[2]  Larry L. Peterson,et al.  Container-based operating system virtualization: a scalable, high-performance alternative to hypervisors , 2007, EuroSys '07.

[3]  Gábor Terstyánszky,et al.  Buttressing volatile desktop grids with cloud resources within a reconfigurable environment service for workflow orchestration , 2014, Journal of Cloud Computing.

[4]  A. Kivity,et al.  kvm : the Linux Virtual Machine Monitor , 2007 .

[5]  Michel Dagenais,et al.  Internal Clock Drift Estimation in Computer Clusters , 2008, J. Comput. Networks Commun..

[6]  Michel Dagenais,et al.  Efficient Model to Query and Visualize the System States Extracted from Trace Data , 2013, RV.

[7]  M. Desnoyers,et al.  The LTTng tracer: A low impact performance and behavior monitor for GNU/Linux , 2006 .

[8]  Michel Dagenais,et al.  State History Tree: An Incremental Disk-Based Data Structure for Very Large Interval Data , 2013, 2013 International Conference on Social Computing.

[9]  Steven J. Vaughan-Nichols,et al.  New Approach to Virtualization Is a Lightweight , 2006, Computer.

[10]  Xiaohui Gu,et al.  PerfScope: Practical Online Server Performance Bug Inference in Production Cloud Computing Infrastructures , 2014, SoCC.

[11]  Michel Dagenais,et al.  Accurate offline synchronization of distributed traces using kernel-level events , 2010, OPSR.

[12]  Masoume Jabbarifar On Line Trace Synchronization for Large Scale Distributed Systems , 2013 .

[13]  Andrew Warfield,et al.  Xen and the art of virtualization , 2003, SOSP '03.

[14]  Hai Jin,et al.  Future Generation Computer Systems , 2022 .

[15]  Xiaohui Gu,et al.  PerfCompass: Toward Runtime Performance Anomaly Fault Localization for Infrastructure-as-a-Service Clouds , 2014, HotCloud.