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

Optimizing a workflow of a storlet architecture

專利號
US11175962B2
公開日期
2021-11-16
申請人
International Business Machines Corporation(US NY Armonk)
發(fā)明人
Sasikanth Eda; Deepak R. Ghuge; Kaustubh I. Katruwar; Sandeep R. Patil
IPC分類
G06F9/46; G06F9/50
技術(shù)領(lǐng)域
storlet,metadata,algorithm,in,storage,may,unit,or,node,nodes
地域: NY NY Armonk

摘要

A computer-implemented method according to one embodiment includes identifying virtualization unit metadata for each of a plurality of nodes, the virtualization unit metadata including one or more guidelines for an application that is implemented by a virtualization unit, where the one or more guidelines include one or more benefits of a virtualization unit, one or more limitations of the virtualization unit, and one or more operating costs of the virtualization unit; determining, from the plurality of nodes, an optimal node for implementing a computation algorithm based on one or more required computation operations and the virtualization unit metadata for each of the plurality of nodes; and returning an identification of the optimal node.

說明書

Further, in one embodiment, the plurality of nodes may be included within a storlet architecture. For example, the storlet architecture may include a compute engine embedded object storage. In another example, each node within the storlet architecture may have an associated virtualization unit (e.g., a virtual machine, etc.). For instance, the virtualization units may include Linux? containers, a Docker? software container, a ZeroVM? process virtualization, etc.

Further still, in one embodiment, when a computation algorithm is assigned to one of the plurality of nodes, the associated virtualization unit of the node may implement the computation algorithm (e.g., by performing the one or more computation tasks indicated within the computation algorithm, etc.). In another embodiment, the computation algorithm may be deployed by an end user. For example, the computation algorithm may be deployed using a GUI, etc. In another example, the computation algorithm may be deployed utilizing a normal object PUT operation.

Also, in one embodiment, the computation algorithm may be received utilizing hooking. For example, a hook may be placed in a storlet engine execution cycle. In another example, the hook may intercept the computation algorithm as it is received within the storlet architecture.

權(quán)利要求

1
微信群二維碼
意見反饋