Virtual Function Mapping for PNIC Failure Recovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems lack effective mechanisms to maintain direct hardware access to network interface cards (NICs) in the event of failure, disrupting network traffic transmission between virtual machines and physical network devices.
Innovation Solution
The implementation of virtual function mappings between virtual machines and physical network interface cards (PNICs) allows for the selection and activation of a new PNIC to replace a failed one, maintaining direct hardware access by creating a new virtual function mapping, thereby ensuring continuous network traffic transfer without requiring hypervisor processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a virtual machine is mapped to a physical network interface card for direct hardware access, then network traffic transmission efficiency is improved, but system reliability deteriorates when the PNIC fails
Solution Approach 1:
The system pre-configures multiple physical network interface cards (PNICs) in the host computer system before any failure occurs. When a PNIC fails, the system can immediately activate a standby PNIC and re-establish the virtual function mapping, avoiding complete network interruption. This preliminary preparation of backup hardware directly addresses the reliability concern while maintaining the direct hardware access efficiency.
Solution Approach 2:
The system dynamically changes the hardware assignment parameter by switching the virtual machine's direct hardware access from a failed PNIC to a different PNIC. The virtual function mapping is reconfigured to associate the virtual machine with a new physical network device, thereby maintaining network connectivity and reliability without sacrificing the performance benefits of direct hardware access.
2Speed
If direct hardware access is implemented between virtual machines and PNICs, then network traffic processing speed is improved, but ease of repair deteriorates when hardware failure occurs
Solution Approach 1:
Multiple PNICs are pre-installed and configured in the system before any failure occurs. The link aggregator is pre-configured with the capability to detect failures and switch to backup PNICs. This preliminary setup enables rapid fault isolation and hardware replacement without disrupting the direct hardware access architecture, thereby maintaining processing speed while improving ease of repair.
Solution Approach 2:
The network interface functionality is segmented across multiple independent PNICs rather than relying on a single hardware device. This segmentation allows the system to isolate failures to individual PNICs while maintaining overall network functionality through alternative cards, making fault diagnosis and hardware replacement simpler and faster.
3Reliability
If multiple PNICs are configured for redundancy, then system reliability is improved, but device complexity increases
Solution Approach 1:
The link aggregator implements automated failure detection and PNIC switching functionality, eliminating the need for manual intervention when hardware failures occur. The system automatically monitors PNIC status, detects failures, selects appropriate backup PNICs, and reconfigures virtual function mappings without administrator involvement. This self-service capability manages the complexity of multiple PNICs while maintaining high reliability.
Solution Approach 2:
Multiple PNICs are configured with identical functionality and capability to serve the same virtual machines. Each PNIC can independently handle network traffic and establish virtual function mappings, making them interchangeable. This multi-functionality allows any PNIC to replace any other, simplifying the management of redundant hardware while ensuring system reliability.
Data Source
AI summary
A system for maintaining direct hardware access in the event of PNIC failure. A host for the system includes: a processor; a first and a second PNIC, where the first PNIC is activated and all other PNICs are deactivated; a host operating system; a virtual machine; and a hypervisor for transferring packets between the host operating system and the virtual machine. The host operating system includes a link aggregator, multiple host VNICs, and a virtual switch associated with the VNICs. The first virtual machine includes a virtual network protocol stack and a guest VNIC. The link aggregator is configured to determine whether the first PNIC has failed. Based on a determination that the first PNIC has failed, the link aggregator is further configured to: remove a virtual function mapping between the first PNIC and the virtual machine; determine the second PNIC; deactivate the first PNIC; and activate the second PNIC.