Browse Prior Art Database

Predictive Hot Standby USB Hypervisor

IP.com Disclosure Number: IPCOM000198384D
Publication Date: 2010-Aug-06
Document File: 2 page(s) / 23K

Publishing Venue

The IP.com Prior Art Database

Abstract

Disclosed herein is the addition of a second hypervisor port to a device. This facilitates redundancy for solid state devices in order to keep the power overhead to a minimum by only powering on the secondary key when a failure is approaching in the primary key. This is determined by reading the counter registers on either the solid state device itself, the USB host Controller, or using bad block management. At that point, the system copies data from the primary to the secondary key, where it is held until the primary key is replaced.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 57% of the total text.

Page 1 of 2

Predictive Hot Standby USB Hypervisor

As more markets move toward virtualization solutions, the need for redundant hypervisors is more prevalent. Today most servers only have a single USB port used for the purpose of holding the virtual operating system; those ports are powered as soon as a key is inserted. Multiple solid state devices unnecessarily power on simultaneously.

There are no solutions for this problem. Methods currently exist to backup to a spare HDD when a failure occurs, but there are none for solid state devices and the HDDs are powered on all of the time.

This disclosure explains how to have multiple solid state devices present simultaneously, but only power on the secondary solid state devices when the primary device is no longer at its peak usability state.

Solid state devices have a set number of writes before they reach end of life. Devices also maintain a bad block manager where the number of bad sectors is kept. This disclosure attempts to reach power efficiency by having only the primary key powered on until one of the failure states is approaching (e.g., either there are too many bad blocks present to continue writing or the maximum amount of writes is approaching). When the system detects a Predictive Failure Analysis (PFA) event, it copies data to the secondary key from the primary. As the secondary key becomes primary, the system puts the failed key into a standby state. This allows redundancy without the extra overhead of powering mult...