JPS6039248A - Resource managing system - Google Patents

Abstract

PURPOSE:To improve the processing efficiency by excluding a real memory used by a high priority program and using the rest without swap-out of all memories when a memory load is high and does not satisfy the working set size of a program having minimum execution priority. CONSTITUTION:The real memory 1 of resource management system is provided with a program storage area 2, a memory managing table 3, an idle area management table 4, a mapping control table 5 and an execution priority managing table 6, and a memory control mechanism 7 execute control and data transfer is connected to each. A processing device 8 executing the program is connected to the mechanism 7 via a data transfer line 17 and a CPU control mechanism 14. Further, an auxiliary storage device 16 is connected to the transfer line 16 via an auxiliary storage controller 15. When the memory load does not satisfy the working set size of the minimum execution priority program, all memories are avoided from being swapped out, the real memory used by the high priority program is excluded, the rest is used to improve the utilizing efficiency.

Description

DETAILED DESCRIPTION OF THE INVENTION The present invention provides a real memory management method in a data processing device;
In particular, the present invention relates to a resource management method that can efficiently allocate real memory to a plurality of sequential programs that are being executed simultaneously when the system runs out of real memory.

(Prior Art) In a virtual memory type information processing system that operates with multiple programs, the problem is how to allocate real memory IJi to each program on real memory. In a virtual memory system, a processing unit CPU advances processing while accessing real memory in which a part of a program to be executed is stored. The entire program is stored on the auxiliary storage device, and the entire zologram is not always accessed. Therefore, parts with a high probability of being accessed are selected for each page, which is the management unit of the program (this is called the working set). (call) into real memory that can be directly accessed by the CPU. This allows many programs to be executed simultaneously with a small amount of real memory, increasing the efficiency of using real memory resources.

If the information that the CPU attempts to access does not exist in the real memory (when shifted), the contents of the desired logical page of the program are transferred from the auxiliary storage device to the appropriate physical page of the real memory. Prior to this transfer, if there is already no free real memory, the old information that is in the page of the real memory to which the new information is to be transferred is transferred to the auxiliary storage and saved. If the amount of real memory given to a program is smaller than the amount of real memory required by the program (working set size), the probability that the desired program's logic waveforms are not in real memory increases, and the transfer described above increases. is carried out frequently. Therefore, the program waits for transfer and is not executed. To prevent this, normally when a page fault occurs, the contents of real memory being used by other programs are transferred to auxiliary storage to create free real memory, and this is allocated to the program to satisfy the working set size. Reduce the number of times K-shift occurs.

In a multiprogramming system, a large number of programs are processed simultaneously by time sharing, but when the above transfer starts and the program cannot be executed, the CPU executes another program. However, if the total amount of real memory required for all programs (sum of working set sizes) exceeds the total amount of real memory in the / stem, real memory requests will occur one after another each time control is transferred to each program.
Since the real memory resources are competed between programs, the above-mentioned transfer to create a dead memory and the transfer of the necessary logic contents from the auxiliary storage device to the real memory occur frequently in all programs. As a result, all programs have a large amount of waiting time for transfer, and the execution of the programs does not proceed (thrashing state).

Conventionally, in order to prevent this thrashing, all the contents of the real memory used by the program with the lowest execution priority are forcibly transferred to the auxiliary storage device, regardless of the amount of real memory that is insufficient, to create free real memory. l) Create k (swap out)
,The insufficient amount of real memory was allocated to other programs with high execution priority. Swap-out has the disadvantage that it is insufficient and wastes a lot of memory, and that real memory remains unused, making it impossible to effectively utilize memory resources. Still, the program with the lowest execution priority is forcibly taken away from all real memory by swapping out, so that program cannot be executed at all. As a result, even when other programs cannot be executed due to waiting for input/output, etc., this program cannot be executed, resulting in the disadvantage that the CPU of any program is not used and is wasted.

(Objective of the Invention) In order to eliminate these drawbacks, the present invention has the following objectives: (1) When the total amount of real memory required by each program exceeds the total amount of real memory of the system, (1) one of the programs belonging to the lowest execution priority is By selecting the actual memo 'Jk' that is currently in use and transferring its contents to the auxiliary storage device, free memory is created and given to other programs that have a shortage of real memory, but the rest is (11) When the program to which memory is to be taken is hard-shifted, memory is not given to the program in excess of the amount of real memory currently in use by the program. This prevents the program from stealing the real memory used by the high-priority program, thereby suppressing the occurrence of thrashing in the high-priority program, and (lii) Set only the lowest execution priority to 17, other higher execution priority programs are CPU, auxiliary storage controller (channel)
By giving these remaining system resources to the program only when it is not in use, the use of system resources that would otherwise be used to handle page faults that occur frequently in the program can be reduced.
To prevent execution interruption of high execution priority programs.

This is achieved by a resource management method that combines a memory schedule and a CPU schedule, and will be explained in detail below with reference to the drawings.

(Structure and operation of the invention) FIG. 1 is a block diagram showing the structure of an embodiment according to the method of the present invention, and 1 is an actual memo in which a program P is stored at the time of execution! In I (MM), Po~P is the zologram name and 2 is the program? In the program storage areas on the real memory, PAo-PAn are areas storing a part of each program pop, and 3 is an area for each program P. -Amount of real memory in use (working set size) per P
S and a pointer P to its mapping control table 5
4 is a memory management table that manages the TR, 4 is a free real memory management table that manages the free real memory amount E and its physical number PPAGE, and 5 is a correspondence between the program's logical page number LPAGE and the physical page number PPAGE of the real memory. and a flag A'f indicating whether the contents of the logical wave are already in the physical wave on the real memory. Mapping control table 6 is managed for each program. 7 is a memory control mechanism that controls memory and transfers data; 8 is a processing unit (CPU) which is an execution unit for executing programs; 9 is each program P; A mapping control mechanism 10 converts between the logical page number LPAGE of Pn and the physical page number PPAGE and detects a page fault; A selection mechanism 11 transfers the contents of the physical page of the real memory to a logical page on the auxiliary storage device 16 to make the real memory free, and 12 a page-out control mechanism that transfers the contents of the physical page of the real memory to a logical page on the auxiliary storage device 16. a page-in control mechanism that transfers the contents to a free real memory and makes the physical page containing the contents of the logical page of the program P desired by the processing unit (CPU) 8 accessible;
14 is an execution priority control mechanism that changes the execution priority of a program; 14 is a CPU control mechanism that controls the entire processing device 8 and transfers data; and 15 is an auxiliary storage that controls auxiliary storage and data transfer. A control device 16 is an auxiliary storage device in which all logical pages of programs Po to Pn are stored, 17 is a real memory (MM) 1 , a processing device (CPU) 8, and an auxiliary storage device 16 for data transfer between them. It is a data transfer path. Note that the value of flag A in the mapping control table 5 is 1 if the content of the logical page already exists in any physical page, and O if the content does not exist.

Next, the operation will be explained. The processing device 8 proceeds with the processing while accessing the PA of the novel program storage area 2 on the real memory. In the virtual memory system, the entire program Po-Pn is stored on the auxiliary storage device 16, and the contents of the logical waves of each 70 programs P are stored in the real memory 1 through the data transfer path 17 when needed. It is copied to the physical page in PAi of area 2 and becomes accessible.

When the processing device 8 accesses the program, the logical page number LPAGEj is used to access the program, and this logical page number LPAGEj is once passed to the mapping control mechanism 9. The mapping control mechanism 9 is based on the CPU control mechanism 1.
4((), the memory control mechanism 7 is activated, and the flag A in the entry for the logical page number LPAGEj of the mapping control table 5 and the physical page number PPAGEj are obtained through the data transfer path 17. In this way, the mapping control mechanism 9 is converted into a physical page number PPAGEJ corresponding to the logical R-age number LPAGEj according to the mapping control table 5.Furthermore, the physical page number LPAGEj is transferred from the mapping control mechanism 9 through the entire cp control mechanism 14 and through the data transfer path 17. The data is passed to the memory control mechanism 7. Next, the memory control mechanism 7 takes out the data and transfers it to the desired destination via the data transfer path 17.
The data is transferred to the processing device 8 to complete the access. Logical page LP of the program received by the mapping control mechanism 9
If the value of the flag Aj of the entry corresponding to AGE is 0, that is, the content of the desired logical page LPAGE j is not present in any physical wave (page fault), the mapping control mechanism 9 controls the CPU control mechanism 14iC. -e- Notify occurrence of shift.

For example, the processing when a shift occurs and a real memory request is made during the execution of the program Pi will be explained step by step.

(1) From the mapping control mechanism 9 to the CPU control mechanism 14
(4) When notified of the occurrence of a shift, the CPU control mechanism 14 activates the page selection mechanism 10. The free memory end E of a certain free memory management table 4 is accessed and checked. If the value of E is not 0, that is, if there is free real memory, select the physical wave number 1-2 registered in the table and write the physical wave number PPA.
Logical page number LP where GEk and esfault occurred
AGEj is notified to the page-in control mechanism 12, and the -C<-page-in control mechanism 12 is activated.

0ii) In (ii), free memory entry E is O
If there is no free memory, the page selection mechanism 10 uses the CPU
:Acquires and checks the entries PRo-PRx of the execution priority management table 6 in the real memory 2 through the data transfer path 17 via the li control mechanism 14, and checks the entries PRo-PRx of the execution priority management table 6 in the real memory 2 through the data transfer path 17. One of them is selected as the memory take-up target program Pl. Furthermore, by looking at the mapping control table 5 pointed to by PTRl of the Pl entry in the memory management table 3,
The IK-di PPAGEk is selected from among the physical pages being used by the memory removal target program Pi, and the pageout control mechanism 11 is notified of the memory removal target program name P1 and the selected physical page number PPAGEk, and the page is paged out. The control mechanism 11 is activated. However, if the program Pi that caused the page fault is one of the programs belonging to the lowest execution priority, that program itself is selected as the program to be taken up from the memory 9. Further, at the same time as starting the page-out control mechanism 11 in this way, the execution priority control mechanism 13 is also notified of the program name PI to be taken up from memory, and the execution priority control mechanism 1
Start 3.

(V) When the real memory 1 has a low usage rate and is not in a memory shortage state, the execution priority control mechanism 13 sets the memory removal target program to the lowest execution priority PRx in the system where no program is set. In order to set the zero program P1, the name of the program to be taken up memory P1 is registered in the PRx entry of the execution priority management table 6 via the CPU control mechanism 14 and the data transfer path 17.

Therefore, the program to be taken up of memory runs only when all other programs are not running, and the page fault of that program occurs while the program is running, that is, when all other programs are running on the processing unit 8 and )
This occurs while the page faults are not being used, so an increase in the load on the processing unit 8 and I10 due to frequent page faults does not affect the execution of other programs.

(■) The wave-in control mechanism 11 transfers the contents of the physical PPAGEk notified in (111) to the memory control mechanism 7.
and starts up the auxiliary storage control device 15, and starts the data transfer path 1.
7 from the real memory 1 to the auxiliary storage device 16. After this transfer is completed, the physical page number PPAGEk that has become free due to this process and the logical page number LPAGEj that caused the hard shift by program P1 are subjected to page-in control as in the case (11) where there was already free memory. The mechanism 12 is notified and the a-gein control mechanism 12 is activated.

4-The engine control mechanism 12 is the CPU control mechanism 14
By starting up the memory control mechanism 7 and the auxiliary storage device 15 via the data transfer path 17, the program P1 performs an o-shift from the auxiliary storage device 16 to the requested logical page LPA (Jj). −
Copy it to PPAGEk and make it accessible. Furthermore, the logical page number LPA of the mapping control table 5 is transmitted via the CPU control mechanism 14 and the data transfer path 17.
The physical page number PPAGEk is set in the entry of GEj, and the flag Aj of that entry is set to 1 to indicate that the contents of the logical page already exist in the real memory. Next, the page-in control mechanism 12 notifies the CPU control mechanism 14 that the desired page is now accessible, and completes all page fault processing.

FIG. 2 shows a flowchart of these processes.

An embodiment of the present invention has been described above, but the gist of the present invention is that when the total amount of real memory required by each program exceeds the total amount of real memory of the system, ■ the program belonging to the lowest execution priority is By selecting the actual memory in use corresponding to the amount of insufficient memory from one program and transferring its contents to the auxiliary storage device, free memory is provided to other programs that have insufficient real memory, but the remaining memory is The program to which the memory is being taken can be executed as it is, and if the program to which the memory is to be taken has a peno fault, it is given high priority by not giving memory in excess of the amount of real memory in use by that program. Prevents the actual memo IJ = from being taken away from programs with high execution priority, and suppresses the occurrence of slur songs in high execution priority programs. However, only when another program with a higher execution priority does not use the processing unit 8 or auxiliary storage control unit (channel) 15, these remaining system resources are given to the above program - 1 and the program is used frequently. 1 = - Prevents the use of system resources during fault processing from interfering with the execution of high execution priority programs.

It is a comprehensive resource management method that combines a memory node and a processing unit schedule.

(Effects) As explained above, according to the present invention, even if the working set size of a program with the lowest execution priority is not reached due to high memory load, all real memory used by that program can be swapped out. Lowest execution priority so that all other high-priority programs run when they are not using the processing unit. Since resources are allocated to programs, programs do not run at all as in the conventional system, and reverse processing efficiency is improved.

In particular, programs that have a low execution priority and require a large amount of real memory to the extent that running them will inevitably lead to a memory shortage state, which would be difficult to run using conventional control methods, can now be executed using this control method. Furthermore, even if the system is in a syslashing state with a high memory load, real memory will be taken up by the program with the lowest execution priority to compensate for the shortage of other programs. Since it is executed using only the remaining resources used by
The low execution priority program is automatically stopped, and when the memory load decreases, the low execution priority program is automatically given real memory and restarted. In addition, system driver intervention is required to stop low-priority programs to prevent interference with the execution of high-priority programs, as in the past, and to restart low-priority programs when the system memory load decreases again. There is also the advantage that it becomes unnecessary.

[Brief explanation of drawings]

FIG. 1 is a schematic diagram showing the configuration of an embodiment according to the method of the present invention, and FIG. 2 is a flowchart of the processing of the present invention. 1... Real memory, 2... Program storage area, 3.
... Memory management table, 4... Free real memory management table, 5... Mapping control table, 6... Execution priority management table, 7... Memory control mechanism, 8...
- Processing device, 9... Mapping control mechanism, 1o...
R-no selection mechanism, 11... page-out control mechanism, 1
2...Bage-in control mechanism, 13...Execution priority control mechanism, 14...CPU control mechanism, 15...Auxiliary storage control device, 16...Auxiliary storage device, 17...Data transfer path .

Claims (1)

[Claims] In a virtual memory information processing/system that operates as a multi-zologram and each program is executed according to its execution priority, each zologram is Allocates all real memory to each program in order of execution priority, and when the remaining real memory allocation falls below the real memory requirement of the next program to be allocated, only the remaining amount of real memory is given. , the amount of allocated real memory is required (Real memory) This problem occurs when the execution priority of the program is set to the lowest execution priority in the /system, and competition for real memory occurs due to lack of real memory. A resource management method that requires a mechanism to prevent programs from being unable to run due to frequent transfers of memory contents between real memory and auxiliary storage.