Processing

Please wait...

Settings

Settings

Goto Application

1. US20130290771 - Computer system to switch logical group of virtual computers

Note: Text based on automatic Optical Character Recognition processes. Please use the PDF version for legal matters

[ EN ]

Claims

1. A computer system comprising:
a plurality of computer nodes, each of the plurality of computer nodes comprising a plurality of virtual computers constituting a logical group based on software running on the virtual computers, and a control base unit controlling the plurality of virtual computers,
each virtual computer constituting a multiplexing group with another virtual computer operating on another computer node different from an own computer node on which the virtual computer is operating, with either one operating as a master virtual computer whereas the other operates as a slave virtual computer,
the control base unit managing whether each of the plurality of virtual computers in the own computer node, in which the control base unit is provided, operates as a master virtual computer or a slave virtual computer, and monitoring a state of each of the plurality of virtual computers, and
wherein upon detecting a failure of a virtual computer operating on the own computer node as a master virtual computer, the control base unit decides whether to also switch other virtual computers operating on the own computer node in the logical group along with the virtual computer in which the failure occurred from master virtual computers to slave virtual computers, and exercising control of switching the logical group in accordance with a result of the decision.
2. The computer system according to claim 1, wherein the control base unit decides whether to also switch other virtual computers operating on the own computer node in the logical group along with the virtual computer in which the failure occurred from master virtual computers to slave virtual computers, depending on a ratio of a number of virtual computers operating on the own computer node as master virtual computers to a number of virtual computers operating on the own computer node as slave virtual computers.
3. The computer system according to claim 2, wherein if the number of virtual computers operating on the own computer node as master virtual computers is less than half of a total number of virtual computers operating on the own computer node, the control base unit exercises control to also switch other virtual computers in the logical group operating on the own computer node as master virtual computers along with the virtual computer in which the failure occurred from master virtual computers to slave virtual computers.
4. The computer system according to claim 2, wherein
if the number of virtual computers operating on the own computer node as master virtual computers is at least half of a total number of virtual computers operating on the own computer node, the control base unit exercises control to switch the logical group of the virtual computer in which the failure occurred from master virtual computers to slave virtual computers, and
upon recovery from the failure, the control base unit exercise control to restore the logical group of the virtual computer in which the failure occurred from the slave virtual computers to the master virtual computers.
5. The computer system according to claim 1, wherein when switching one of the virtual computers operating on the own computer node from a master virtual computer to a slave virtual computer, the control base unit transmits a notice of a request of switching to a slave virtual computer to the one of the virtual computers, and to switch another one of the virtual computers that constitutes a multiplexing group with the one of the virtual computers from a slave virtual computer to a master virtual computer, the control base unit transmits a notice to another computer node on which the other one of the virtual computer operates.
6. The computer system according to claim 1, wherein the control base unit manages hardware resources used by respective virtual computers operating on the own computer node, and upon detecting a failure of a hardware resource shared by the logical group of virtual computers operating as master virtual computers, the control base unit exercises control to switch the logical group together from master virtual computers to slave virtual computers.
7. A method executed in a computer system comprising a plurality of computer nodes, each of the plurality of computer nodes comprising a plurality of virtual computers constituting a logical group based on software running on the virtual computers and a control base unit controlling the plurality of virtual computers,
each virtual computer constituting a multiplexing group with another virtual computer operating on another computer node different from an own computer node on which the virtual computer is operating, with either one operating as a master virtual computer whereas the other operates as a slave virtual computer, the method comprising:
managing, by the control base unit, as to whether each of the plurality of virtual computers in the own computer node, in which the control base unit is provided, operates as a master virtual computer or a slave virtual computer;
monitoring, by the control base unit, a state of each of the plurality of virtual computers;
upon detecting a failure of a virtual computer operating on the own computer node as a master virtual computer, deciding, by the control base unit, whether to also switch other virtual computers operating on the own computer node in the logical group along with the virtual computer in which the failure occurred from master virtual computers to slave virtual computers; and
exercising control of switching the logical group in accordance with a result of the decision.
8. The method according to claim 7, wherein the control base unit decides whether to also switch other virtual computers operating on the own computer node in the logical group along with the virtual computer in which the failure occurred from master virtual computers to slave virtual computers, depending on a ratio of a number of virtual computers operating on the own computer node as master virtual computers to a number of virtual computers operating on the own computer node as slave virtual computers.
9. The method according to claim 8, wherein if the number of virtual computers operating on the own computer node as master virtual computers is less than half of a total number of virtual computers operating on the own computer node, the control base unit exercises control to also switch other virtual computers in the logical group operating on the own computer node as master virtual computers along with the virtual computer in which the failure occurred from master virtual computers to slave virtual computers.
10. The method according to claim 8, wherein
if the number of virtual computers operating on the own computer node as master virtual computers is at least half of a total number of virtual computers operating on the own computer node, the control base unit exercises control to switch the logical group of the virtual computer in which the failure occurred from master virtual computers to slave virtual computers, and
upon recovery from the failure, the control base unit exercise control to restore the logical group of the virtual computer in which the failure occurred from the slave virtual computers to the master virtual computers.
11. The method according to claim 7, wherein when switching one of the virtual computers operating on the own computer node from a master virtual computer to a slave virtual computer, the control base unit transmits a notice of a request of switching to a slave virtual computer to the one of the virtual computers, and to switch another one of the virtual computers that constitutes a multiplexing group with the one of the virtual computers from a slave virtual computer to a master virtual computer, the control base unit transmits a notice to another computer node on which the other one of the virtual computers operates.
12. The method according to claim 7, wherein the control base unit manages hardware resources used by respective virtual computers operating on the own computer node, and upon detecting a failure of a hardware resource shared by the logical group operating as master virtual computers, the control base unit exercises control to switch the logical group together from master virtual computers to slave virtual computers.