CN-116760773-B - Adjustment method, device, apparatus, storage medium and computer program product

CN116760773BCN 116760773 BCN116760773 BCN 116760773BCN-116760773-B

Abstract

The present application relates to an adjustment method, an apparatus, a computer device, a computer readable storage medium and a computer program product. The method comprises the steps of obtaining current capacity parameters of a storage system and pressure parameters of current user service of the storage system, wherein the capacity parameters are used for representing processing capacity of the storage system, the pressure parameters are used for representing pressure stability of the user service, adjusting a preset user service token bucket according to the capacity parameters, adjusting a preset background service token bucket according to the capacity parameters and the pressure parameters, responding to the user service based on the adjusted user service token bucket, and responding to the background service based on the adjusted background service token bucket. The adjustment method provided by the application can effectively improve the resource utilization rate of the storage system, thereby effectively improving the service quality of the storage system.

Inventors

LIU LI
LIU LILI
YIN WENJIAN
HAN YONG
WU RUIQIANG

Assignees

天津中科曙光存储科技有限公司

Dates

Publication Date: 20260508
Application Date: 20230516

Claims (10)

1. A method of adjustment, the method comprising: Acquiring current capacity parameters of a storage system and current pressure parameters of user service of the storage system, wherein the capacity parameters are used for representing processing capacity of the storage system, and the pressure parameters are used for representing pressure stability conditions of the user service; Determining a preset adjustment target of a user service token bucket according to the IO accumulation amount, wherein the adjustment target of the user service token bucket comprises an adjustment direction of token attribute parameters and an adjustment step length of the token attribute parameters; Determining a first initial adjustment target of a background service token bucket according to the disc busy parameter and the pressure parameter, determining a second initial adjustment target of the background service token bucket according to the IO accumulation amount, determining a final adjustment target of the background service token bucket according to the first initial adjustment target and the second initial adjustment target, wherein the final adjustment target of the background service token bucket comprises an adjustment direction of a token attribute parameter and an adjustment step length of the token attribute parameter; And responding to the user service based on the user service token bucket after the adjustment processing, and responding to the background service based on the background service token bucket after the adjustment processing.
2. The method of claim 1, wherein the determining a first initial adjustment target for the background traffic token bucket based on the disk busy parameter and the pressure parameter comprises: Determining a first sub-adjustment target of the background service token bucket according to the disk busy parameter; determining a second sub-adjustment target of the background service token bucket according to the pressure parameter; and determining the first initial adjustment target according to the first sub-adjustment target and the second sub-adjustment target.
3. The method of claim 2, wherein the first sub-adjustment target and the second sub-adjustment target each comprise an adjustment direction of a token attribute parameter, wherein the determining the first initial adjustment target based on the first sub-adjustment target and the second sub-adjustment target comprises: Taking the downregulation direction as the token attribute parameter regulation direction of the first initial regulation target under the condition that the regulation directions included by the first sub regulation target and the second sub regulation target have the downregulation direction; And taking the upward adjustment direction as the token attribute parameter adjustment direction of the first initial adjustment target under the condition that the adjustment directions included in the first sub adjustment target and the second sub adjustment target are both upward adjustment directions.
4. The method of claim 2, wherein the first sub-adjustment target and the second sub-adjustment target each comprise an adjustment step size of a token attribute parameter, wherein the determining the first initial adjustment target based on the first sub-adjustment target and the second sub-adjustment target comprises: taking the largest adjustment step length of the adjustment step length included in the first sub-adjustment target and the adjustment step length included in the second sub-adjustment target as the token attribute parameter adjustment step length of the first initial adjustment target under the condition that the token attribute parameter adjustment direction of the first initial adjustment target is the downward adjustment direction; And taking the average value of the adjustment step length included by the first sub-adjustment target and the adjustment step length included by the second sub-adjustment target as the token attribute parameter adjustment step length of the first initial adjustment target under the condition that the token attribute parameter adjustment direction of the first initial adjustment target is the upward adjustment direction.
5. The method of claim 2, wherein the first initial adjustment objective and the second initial adjustment objective each comprise an adjustment direction for token attribute parameters, wherein the determining the final adjustment objective for the background traffic token bucket based on the first initial adjustment objective and the second initial adjustment objective comprises: Taking the down-regulation direction as the token attribute parameter regulation direction of the final regulation target under the condition that the regulation directions included by the first initial regulation target and the second initial regulation target have the down-regulation direction; and taking the up-regulating direction as the token attribute parameter regulating direction of the final regulating target under the condition that the regulating directions included by the first initial regulating target and the second initial regulating target are up-regulating directions.
6. The method according to claim 1, wherein the method further comprises: acquiring a performance upper limit value of the storage system and a first initial value of resources occupied by user service of the storage system; Determining a second initial value of resources occupied by background business of the storage system according to the performance upper limit value of the storage system and the first initial value; And configuring the number of tokens in the user service token bucket according to the first initial value, and configuring the number of tokens in the background service token bucket according to the second initial value.
7. An adjustment device, the device comprising: the system comprises an acquisition module, a storage system management module and a storage system management module, wherein the acquisition module is used for acquiring current capacity parameters of the storage system and current pressure parameters of user service of the storage system, the capacity parameters are used for representing processing capacity of the storage system, the pressure parameters are used for representing pressure stability conditions of the user service, the capacity parameters comprise IO stacking amount and disk busy parameters, and the disk busy parameters are used for representing the busy degree of a disk; The first execution module is used for determining a preset adjustment target of the user service token bucket according to the IO accumulation amount, wherein the adjustment target of the user service token bucket comprises an adjustment direction of token attribute parameters and an adjustment step length of the token attribute parameters; the method comprises the steps of adjusting token attribute parameters of a user service token bucket according to an adjustment target of the user service token bucket, determining a preset first initial adjustment target of a background service token bucket according to a disc busy parameter and a pressure parameter, determining a second initial adjustment target of the background service token bucket according to the IO accumulation amount, determining a final adjustment target of the background service token bucket according to the first initial adjustment target and the second initial adjustment target, wherein the final adjustment target of the background service token bucket comprises an adjustment direction of the token attribute parameters and an adjustment step length of the token attribute parameters, and adjusting the token attribute parameters of the background service token bucket according to the final adjustment target of the background service token bucket; and the second execution module is used for responding to the user service based on the user service token bucket after the adjustment processing and responding to the background service based on the background service token bucket after the adjustment processing.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.

Description

Adjustment method, device, apparatus, storage medium and computer program product Technical Field The present application relates to the field of storage systems, and in particular, to an adjustment method, an adjustment apparatus, a computer device, a computer readable storage medium, and a computer program product. Background The user service refers to a read-write request of a foreground user to the system, and the background service refers to a service which can ensure the normal operation of the storage system, wherein the user service and the background service jointly occupy the resources of the storage system. In the prior art, different token buckets are respectively set for user service and background service so as to realize resource allocation of the user service and the background service. However, the resource allocation achieved by this method generally wastes the resources of the storage system, and cannot be fully utilized, which results in poor service quality of the storage system. Disclosure of Invention In view of the foregoing, it is desirable to provide an adjustment method, apparatus, computer device, computer readable storage medium, and computer program product that can improve the utilization of storage system resources and improve the quality of service of the storage system. In a first aspect, the present application provides a method of adjustment. The method comprises the following steps: The method comprises the steps of obtaining current capacity parameters of a storage system and pressure parameters of current user service of the storage system, wherein the capacity parameters are used for representing processing capacity of the storage system, the pressure parameters are used for representing pressure stability of the user service, adjusting a preset user service token bucket according to the capacity parameters, adjusting a preset background service token bucket according to the capacity parameters and the pressure parameters, responding to the user service based on the adjusted user service token bucket, and responding to the background service based on the adjusted background service token bucket. In one embodiment, the capability parameter comprises IO accumulation amount, the preset user service token bucket is adjusted according to the capability parameter, the method comprises the steps of determining an adjustment target of the user service token bucket according to the IO accumulation amount, wherein the adjustment target of the user service token bucket comprises an adjustment direction of a token attribute parameter and an adjustment step length of the token attribute parameter, and the adjustment of the token attribute parameter of the user service token bucket is performed according to the adjustment target of the user service token bucket. In one embodiment, the capacity parameter further comprises a disk busy parameter, the disk busy parameter is used for representing the busy degree of a disk, the preset background service token bucket is adjusted according to the capacity parameter and the pressure parameter, the capacity parameter further comprises a first initial adjustment target of the background service token bucket according to the disk busy parameter and the pressure parameter, a second initial adjustment target of the background service token bucket according to the IO accumulation amount, a final adjustment target of the background service token bucket according to the first initial adjustment target and the second initial adjustment target, the final adjustment target of the background service token bucket comprises an adjustment direction of a token attribute parameter and an adjustment step length of the token attribute parameter, and the token attribute parameter of the background service token bucket is adjusted according to the final adjustment target of the background service token bucket. In one embodiment, the determining the first initial adjustment target of the background service token bucket according to the disk busy parameter and the pressure parameter comprises determining a first sub-adjustment target of the background service token bucket according to the disk busy parameter, determining a second sub-adjustment target of the background service token bucket according to the pressure parameter, and determining the first initial adjustment target according to the first sub-adjustment target and the second sub-adjustment target. In one embodiment, the first sub-adjustment target and the second sub-adjustment target each include an adjustment direction of the token attribute parameter, and the determining the first initial adjustment target according to the first sub-adjustment target and the second sub-adjustment target includes taking the down adjustment direction as the token attribute parameter adjustment direction of the first initial adjustment target when there is a down adjustment direction in the adjustment directions include