Low overhead hardware-assisted virtual machine analysis and profiling

ABSTRACT: Cloud infrastructure providers need reliable performance analysis tools for their nodes. Moreover, the analysis of Virtual Machines (VMs) is a major requirement in quantifying cloud performance. However, root cause analysis, in case of unexpected crashes or anomalous behavior in VMs, remains a major challenge. Modern tracing tools such as LTTng allow fine grained analysis - albeit at a minimal execution overhead,and being OS dependent. In this paper, we propose HAVAna,a hardware-assisted VM analysis algorithm that gathers and analyzes pure hardware trace data, without any dependence on the underlying OS or performance analysis infrastructure. Our approach is totally non-intrusive and does not require any performance statistics, trace or log gathering from the VM. We used the recently introduced Intel PT ISA extensions on modern Intel Skylake processors to demonstrate its efficiency and observed that, in our experimental scenarios, it leads to a tiny overhead of up to 1%, as compared to 3.6-28.7% for similar VM trace analysis done with software-only schemes such as LTTng. Our proposed VM trace analysis algorithm has also been opensourced for further enhancements and to the benefit of other developers. Furthermore, we developed interactive Resource and Process Control Flow visualization tools to analyze the hardware trace data and present a real-life usecase in the paper that allowed us to see unexpected resource consumption by VMs