Virtual function boot in multi-root I/O virtualization environments to enable multiple servers to share virtual functions of a storage adapter through a MR-IOV switch

Patent metadata

Field	Value
Publication number	US-9135044-B2
Application number	US-201113267646-A
Country	US
Kind code	B2
Filing date	Oct 6, 2011
Priority date	Oct 26, 2010
Publication date	Sep 15, 2015
Grant date	Sep 15, 2015

Abstract

A method for virtual function boot in a system including a single-root I/O virtualization (SR-IOV) enabled server includes loading a PF driver of the PF of a storage adapter onto the server utilizing the virtual machine manager of the server; creating a plurality of virtual functions utilizing the PF driver, detecting each of the virtual functions on an interconnection bus, maintaining a boot list associated with the plurality of virtual functions, querying the storage adapter for the boot list utilizing a VMBIOS associated with the plurality of VMs, presenting the detected boot list to a VM boot manager of the VMM, and booting each of the plurality of virtual machines utilizing each of the virtual functions, wherein each VF of the plurality of VFs is assigned to a VM of the plurality of VMs via an interconnect passthrough between the VMM and the plurality of VMs.

First claim

What is claimed:

1. A method for virtual function boot in a system including a plurality of multi-root I/O virtualization (MR-IOV) servers, at least one MR-IOV switch, and at least one storage adapter including at least one physical function (PF) and configured to implement a plurality of virtual functions, each of the MR-IOV servers being communicatively coupled to the at least one MR-IOV switch, the at least one storage adapter being communicatively couplable to the at least one MR-IOV switch, comprising:
upon interconnection of the at least one storage adapter with the at least one MR-IOV switch, loading a physical function (PF) driver of the at least one storage adapter onto the MR-IOV switch;
creating a plurality of virtual functions (VFs) utilizing the PF driver on MR-IOV switch;
assigning each of the VFs to an MR-IOV server of the plurality of MR-IOV servers;
identifying each of the plurality of VFs as a virtual storage adapter by the plurality of MR-IOV servers, wherein each MR-IOV server identifies a VF as a virtual storage adapter;
loading a UEFI driver onto each of the VFs;
obtaining a boot list associated with the plurality of virtual functions from firmware of the at least one storage adapter utilizing the UEFI driver loaded on each of the VFs, wherein the boot list is configured to associate each virtual function with a corresponding boot disk; and
booting a plurality of boot disks utilizing each of the VFs assigned to each of the MR-IOV servers utilizing the obtained boot list.

2. The method of claim 1 , wherein the interconnection of the at least one storage adapter with the at least one MR-IOV switch comprises:
interconnecting the at least one storage adapter to the MR-IOV switch via a PCIe interconnecton bus.

3. The method of claim 1 , wherein the storage adapter comprises:
a MegaRAID card.

4. The method of claim 1 , wherein each of the MR-IOV servers is communicatively coupled to the at least one MR-IOV switch via a PCIe interconnection link.

5. The method of claim 1 , wherein the loading a UEFI driver onto each of the VFs comprises:
loading a UEFI driver onto each of the VFs utilizing at least one of UEFI or BIOS.

6. The method of claim 1 , further comprising:
providing a diagnostic message indicative of a status of at least one virtual function drivers.

7. The method of claim 6 , wherein the providing a diagnostic message indicative of a status of at least one virtual function drivers comprises:
transmitting a status signal from the at least one virtual function driver to the at least one storage adapter, the status signal being indicative of the status of the at least one virtual function driver;
storing information associated with the status signal utilizing firmware of the at least one storage adapter;
relaying the status signal from the at least one storage adapter to the PF driver in the MR-IOV switch;
relaying the status signal from the PF driver to at least one of an error handler of the MR-IOV or management tool of the MR-IOV; and
transmitting a user signal to a user interface from the management tool, wherein the user signal is configured to trigger a pre-determined message selected based on a characteristic of the status signal.

8. A system for virtual function boot in a system comprising:
at least one MR-IOV switch;
a plurality of multi-root I/O virtualization (MR-IOV) servers, each of the plurality of MR-IOV servers being communicatively coupled to the MR-IOV switch via a PCIe link; and
at least one storage adapter including at least one physical function (PF), the at least one storage adapter configured to implement a plurality of virtual functions, the at least one storage adapter being communicatively couplable to the at least one MR-IOV switch via a PCIe slot of the MR-IOV switch, wherein, upon interconnection of the at least one storage adapter with the at least one MR-IOV switch, the at least one storage adapter, the MR-IOV switch, and the plurality of MR-IOV servers are configured to:
load a physical function (PF) driver of the at least one storage adapter onto the MR-IOV switch;
create plurality of virtual functions (VFs) utilizing the PF driver on MR-IOV switch;
assign each of the VFs to an MR-IOV server of the plurality of MR-IOV servers;
identify each of the plurality of VFs as a virtual storage adapter by the plurality of MR-IOV servers, wherein each MR-IOV server identifies a VF as a virtual storage adapter;
load a UEFI driver onto each of the VFs;
obtain a boot list associated with the plurality of virtual functions from firmware of the at least one storage adapter utilizing the UEFI driver loaded on each of the VFs, wherein the boot list is configured to associate each virtual function with a corresponding boot disk; and
boot a plurality of boot disks utilizing each of the VFs assigned to each of the MR-IOV servers utilizing the obtained boot list.

9. The system of claim 8 , wherein the MR-IOV switch is configured to perform multi-node clustering utilizing a single storage adapter, wherein a first virtual function is assigned to a first MR-IOV server and a second virtual function is assigned to at least a second MR-IOV server utilizing the MR-IOV switch.

10. The system of claim 8 , wherein the at least one MR-IOV switch includes a first MR-IOV switch and a second MR-IOV switch configured to perform multi-node clustering utilizing two storage adapters, wherein a first virtual function from a first storage adapter is assigned to at least a first MR-IOV server utilizing the first MR-IOV switch and a second virtual function from a second storage adapter is assigned to the first MR-IOV server utilizing the second MR-IOV switch.

Assignees

• Maharana Parag R
• Avago Technologies General Ip

Inventors

• Maharana Parag R

Classifications

• G06F9/4416 Primary

  Network booting; Remote initial program loading [RIPL] · CPC title

• G06F3/0689

  Disk arrays, e.g. RAID, JBOD · CPC title

• G06F9/45558 Primary

  Hypervisor-specific management and integration aspects · CPC title

• G06F2009/45579

  I/O management, e.g. providing access to device drivers or storage · CPC title

• G06F13/4282

  on a serial bus, e.g. I2C bus, SPI bus (on daisy chain buses G06F13/4247) · CPC title