ReNIC: Architectural extension to SR-IOV I/O virtualization for efficient replication

  • Authors:

  • Yaozu Dong;Yu Chen;Zhenhao Pan;Jinquan Dai;Yunhong Jiang

  • Affiliations:

  • Intel Asia-Pacific Research and Development Ltd., P. R. China;University of Tsinghua, P. R. China;University of Tsinghua, P. R. China;Intel Asia-Pacific Research and Development Ltd., P. R. China;Intel Asia-Pacific Research and Development Ltd., P. R. China

  • Venue:
  • ACM Transactions on Architecture and Code Optimization (TACO) - HIPEAC Papers
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Virtualization is gaining popularity in cloud computing and has become the key enabling technology in cloud infrastructure. By replicating the virtual server state to multiple independent platforms, virtualization improves the reliability and availability of cloud systems. Unfortunately, existing Virtual Machine (VM) replication solutions were designed only for software virtualized I/O, which suffers from large performance and scalability overheads. Although hardware-assisted I/O virtualization (such as SR-IOV) can achieve close to native performance and very good scalability, they cannot be properly replicated across different physical machines due to architectural limitations (such as lack of efficient device state read/write, buffering outbound packets, etc.). In this paper, we address those architectural limitations, by proposing ReNIC, an architectural extension to SR-IOV I/O virtualization for efficient I/O replications. We have extended Xen hypervisor and the Remus rapid checkpoint solution to support this new architectural extension. We developed a system simulator on multi-core systems to extensively evaluate ReNIC. The experimental results demonstrate that ReNIC achieves up to 54% CPU usage reduction, compared to software based I/O virtualization at runtime, and up to 16.2% performance advantage over software based I/O virtualization in rapid checkpoint. During migration, ReNIC reduces service shutdown time by about 50%, compared to device emulation and paravirtualized I/O, and over 71% compared to teaming driver.