| 摘要 |
Embodiments relate to searching a cloud-based file storage system using a set of expandable probes. Platforms and techniques are provided to search for a file whose location in cloud storage resources is recorded in a consistent hash ring structure. In a hash ring, a file name can generate a hash output corresponding to a position around a circle. The closest clockwise node to that location can contain the file itself, or a link to another location containing or leading to the file. When a link has become obsolete and no longer points to the file, it may be necessary to search for that file. Embodiments perform a graduated search for the missing file, starting one node from the original node, then trying two adjacent nodes, then four adjacent nodes and so forth in expanding fashion, until the file is found or the hash structure is exhausted. |
| 主权项 |
1. A method comprising:
initiating, by a processor of a centralized server of a cloud management system, a search for a file stored in a cloud-based network, the search based on a plurality of nodes in a hash structure storing a plurality of file links, wherein the search is initiated at a first starting node of the hash structure; searching, by the processor of the cloud management system, a first subset of the plurality of nodes to find the file using a first iteration of an expandable set of probes spanning the first subset of the plurality of nodes, starting at the first starting node, wherein the searching the first subset of the plurality of nodes using the first iteration of the expandable set of probes comprises transmitting a respective probe to a respective target node of the first subset of the plurality of nodes to locate the file at the respective target node; and upon not finding the file in the first subset of the plurality of nodes by the first iteration of the expandable set of probes, performing, by the processor of the cloud management system, an expanded search comprising: expanding the expandable set of probes from a first number of probes in the first iteration to a second number of probes in a second iteration spanning a second subset of the plurality of nodes that is at least double the number of the first subset of the plurality of nodes, wherein the second number of probes in the expandable set of probes in the second iteration is based on a function applied to the first number of probes in the expandable set in the first iteration, and searching, by the processor of the cloud management system, the second subset of the plurality of probes to find the file using the second iteration of the expandable set of probes spanning the second subset starting at a second starting node, wherein the searching the second subset of the plurality of nodes using the second iteration of the expandable set of probes comprises transmitting a first probe to a first target node of the second subset while concurrently transmitting a second probe to a second target node of the second subset to locate the file at the first target node or the second target node, wherein the second starting node is determined by incrementing by one position in the hash structure from a last node of the first subset of the plurality of nodes. |
