白丝美女被狂躁免费视频网站,500av导航大全精品,yw.193.cnc爆乳尤物未满,97se亚洲综合色区,аⅴ天堂中文在线网官网

Determine a load balancing mechanism for allocation of shared resources in a storage system using a machine learning module based on number of I/O operations

專(zhuān)利號(hào)
US11175958B2
公開(kāi)日期
2021-11-16
申請(qǐng)人
INTERNATIONAL BUSINESS MACHINES CORPORATION(US NY Armonk)
發(fā)明人
Lokesh M. Gupta; Matthew R. Craig; Beth Ann Peterson; Kevin John Ash
IPC分類(lèi)
G06F9/50; G06N3/08; G06N20/00
技術(shù)領(lǐng)域
tcbs,learning,storage,in,machine,host,module,adapter,controller,resources
地域: NY NY Armonk

摘要

A plurality of interfaces that share a plurality of resources in a storage controller are maintained. In response to an occurrence of a predetermined number of operations associated with an interface of the plurality of interfaces, an input is provided on a plurality of attributes of the storage controller to a machine learning module. In response to receiving the input, the machine learning module generates an output value corresponding to a number of resources of the plurality of resources to allocate to the interface in the storage controller.

說(shuō)明書(shū)

In certain embodiments, a plurality of device adapters 218, 220 may provide an interface between the storage controller 102 and the plurality of storage devices 110, 112. A plurality of host bus adapters 222, 224 may provide an interface between the storage controller 102 and the plurality of hosts 202, 204. In FIG. 2, the device adapter 218 and the host bus adapter 222 are included in server 206, and the device adapter 220 and host bus adapter 224 are included in server 208.

Task control block or other resources may be used for any of the interfaces such as ports of the host bus adapter and/or ports of the device adapters 218, or any other interface of the storage controller 102. The resources 226 used by the interfaces may include memory, storage, TCBs or any other type of resource. Thus the embodiments are not limited to TCBs and ports of host bus adapters, and may encompass any types of resources and interfaces of the storage controller 102.

FIG. 3 illustrates a block diagram 300 that shows a machine learning module 302 (corresponds to machine learning module 106 shown in FIG. 1) for determination of optimal resource allocation for interfaces, in accordance with certain embodiments. The block diagram 300 shows that the machine learning module 106 comprises a single-output neural network 302.

權(quán)利要求

1
微信群二維碼
意見(jiàn)反饋