摘要:
A plural-OS run system in which a plurality of operating systems (OSs) capable of operating on machines of different architectures, respectively, are allowed to run on one bare machine under the control of one control program (CP) or one control means. The input/output instruction and input/output interrupt of the operating system capable of running on a machine of the same architecture as that of the bare machine are directly executed on the bare machine without need for translation of the format. The input/output instruction and the input/output interrupt of the operating system adapted to run on a machine of the architecture differing from that of the bare machine are allowed to be directly executed while translating the format.
摘要:
In a computer system having a central processing unit, a main storage and at least one I/O device, a plurality of operating systems (OS) can simultaneously run under the control of a control program. For executing an I/O instruction using a central processing unit, a plurality of resident areas of said main storage which do not overlap one another are assigned, under the control of the control program, to the plurality of OSs as main memories therefore, respectively. In responding to an I/O instruction issued by a running one of said plural OSs, an address of said main memory assigned to said running OS which participates in an I/Oo operation requested by said I/O instruction is determined without intervention of the control program, and the address is translated into an address of the main storage of the computer system without intervention of said control program. The I/O operation is then executed by using the address resulting from said address translation.
摘要:
An address translation apparatus is provided which has an address translation look-aside buffer with an entry composed of a real address field, virtual machine identifier field and space identifier field. For the translation look-aside buffer entry to be used by a general virtual machine which uses a plurality of address spaces, a virtual machine identifier for discrimination of a general virtual machine is stored in the virtual machine identifier field, and information used in discriminating an address space is stored in the space identifier field. For the translation look-aside buffer entry to be used by a dynamic address translation off (DATOFF virtual) machine which uses a single address space, an identifier commonly assigned to a group of DATOFF virtual machines is stored in the virtual machine identifier field, and a control block address used in discriminating a DATOFF virtual machine is stored in the space identifier field.
摘要:
A system and method for continuous operation of a virtual machine system having operation modes including a guest mode in which virtual machines are operated and a nonguest mode in which a virtual machine monitor for controlling the virtual machines is operated. The continuous guest is a virtual machine which does not stop executing operation at the occurrence of a failure due to program error of the virtual machine monitor. A main storage is provided with two areas. One of the two areas is a continuous guest area having the same host absolute address in the nonguest mode as a guest absolute address in the guest mode, the area is used by the continuous guest which is a virtual machine which continues to operate on transition of the operation mode from the guest mode to the nonguest mode. The other is an area in which a program module for dispatching the continuous guest in response to the transition of the operation mode from the guest mode to the nonguest mode. The continuous guest is allocated to the guest area on transition of the operation mode from the guest mode to the nonguest mode. Occurrence of a failure due to a program error of the virtual machine monitor is detected and by starting the program module for dispatching the continuous guest in response to the detection of the occurrence of the failure, the operation of the continuous guest does not stop executing.
摘要:
A virtual machine system in which a plurality of operating systems (OS's) can run on one computer including a physical main storage (physical MS), and at least one physical extended storage (physical ES), each operating system (OS) of the OS's having a virtual MS on the physical MS and at least one virtual ES on the at least one physical ES. The system includes a first address translator for translating a virtual ES address designated by an instruction issued by one OS of the OS's on a virtual space generated by the one OS on one virtual ES of the at least one virtual ES of the one OS to a virtual physical ES address on the one virtual ES based on the virtual ES address and an address of an ES relocation table on the virtual MS of the one OS or an ES relocation register in the computer, the one virtual ES being on one physical ES of the at least one physical ES of the computer, and a second address translator for translating the virtual physical ES address to a physical ES address on the one physical ES based on the virtual physical ES address and a start address of the one virtual ES in the one physical ES.
摘要:
In a virtual machine system (VMS) capable of concurrently running at least one operating system (OS) under one real computer system and a control program (VMCP) for controlling the VMS, the object is to reduce the overhead produced for simulating VM I/Os by direct I/O execution. A VM information area of a real sub-channel control block has a status field in which a flag indicating that the sub-channel is dedicated or not is contained. When the flag is "0", it means that the sub-channel is dedicated to the VM and the sub-channel scheduling by the VMCP is not necessary. As a real interruption priority order is dedicated to a VM, only I/O interruption requests of the VM are queued into the real interruption request queue of that dedicated priority order, and the mixing of VMs in that real interruption priority order is avoided. When an interruption control mask of an interruption priority order of the OS on the VM is "0" indicating that the interruption is not acceptable by the VM, the interruption control mask of the corresponding dedicated real interruption priority order is also "0" and the hardware interruption does not take place. Accordingly, the interruption is retained by the hardware and the I/O interruption retention for the VM by the VMCP is avoided.
摘要:
In a virtual machine system (VMS) capable of concurrently running at least one operating system (OS) under one real computer system and a control program (VMCP) for controlling the VMS, the object is to reduce the overhead produced for simulating VM I/Os by direct I/O execution. A VM information area of a real sub-channel control block has a status field in which a flag indicating that the sub-channel is dedicated or not is contained. When the flag is "1", it means that the sub-channel is dedicated to the VM and the sub-channel scheduling by the VMCP is not necessary. As a real interruption priority order is dedicated to a VM, only I/O interruption requests of the VM are queued into the real interruption request queue of that dedicated priority order, and the mixing of VMs in that real interruption priority order is avoided. When an interruption control mask of an interruption priority order of the OS on the VM is "0" indicating that the interruption is not acceptable by the VM, the interruption conrol mask of the corresponding dedicated real interruption priority order is also "0" and the hardware interruption does not take place. Accordingly, the interruption is retained by the hardware and the I/O interruption retention for the VM by the VMCP is avoided.
摘要:
In a virtual machine system in which a virtual machine directly executes operations by use of the hardware without an intervention from the virtual machine control program (VMCP), at an occurrence of an input/output interruption, the system sets to a storage an event that the input/output interruption has been accepted and reserved by the VMCP. When the virtual machine processes interruption information by means of the hardware without an intervention of the VMCP, the virtual machine resets the state of the storage. When the virtual machine is set to an interruptible state, control is passed to the VMCP. The VMCP tests to determine whether or not the virtual machine has reset the state of the storage, thereby judging an acceptability of the interruption.
摘要:
A virtual machine control method for a supercomputer enables a plurality of virtual machines to use a vector processor. Control of the use of the vector processor is through the scalar processor. When a virtual machine requires use of the vector processor, it is first determined whether one of the other virtual machines operating systems is using the vector processor. If not, the scalar processor is dispatched to the operating system requesting use of the vector processor. If another virtual machine operating system is using the vector processor, then the operating system requesting use of the vector processor is placed in a wait state until the vector processor becomes free, whereupon the scalar processor is dispatched to the operating system that had been in the wait state. The condition of the vector processor being free can be communicated directly to the scalar processor without the intervention of the virtual machine monitor.
摘要:
An I/O control system in a virtual machine system has at least one virtual machine (VM) running under control of a virtual machine control program (VMCP) and has a direct I/O execution mode in which an I/O interruption to the I/O device dedicated by the running VM is directly executed without intervention of the VMCP and an indirect I/O execution mode in which the I/O interruption is simulated. The I/O control system comprises identification portion for identifying the I/O device requesting the switching to the direct I/O execution mode, judge portion for judging a mode switching condition and mode selection portion for selecting one of the two modes. If the VM which contemplates the direct execution has not yet dedicated the I/O device requesting the mode switching, it dedicates the I/O device, and if the VM has not yet dedicated an I/O interrupt subclass which controls the I/O interruption of the I/O device, it dedicates the subclass, and the I/O device in the indirect I/O execution mode is switched to the direct I/O execution mode.