US 12,124,334 B2
Methods and devices for failovers in processing nodes for collaborative computing
Junhua He, Shenzhen (CN); Baoyuan Liu, Shenzhen (CN); Xiang Zeng, Shenzhen (CN); and Boping Yu, Shenzhen (CN)
Assigned to Tencent Technology (Shenzhen) Company Limited, Shenzhen (CN)
Filed by Tencent Technology (Shenzhen) Company Limited, Shenzhen (CN)
Filed on May 13, 2022, as Appl. No. 17/743,837.
Application 17/743,837 is a continuation of application No. PCT/CN2021/097956, filed on Jun. 2, 2021.
Claims priority of application No. 202010652008.1 (CN), filed on Jul. 8, 2020.
Prior Publication US 2022/0269564 A1, Aug. 25, 2022
Int. Cl. G06F 11/00 (2006.01); G06F 9/50 (2006.01); G06F 11/07 (2006.01); G06F 11/14 (2006.01); G06F 11/20 (2006.01); H04L 41/0668 (2022.01); G06F 9/48 (2006.01)
CPC G06F 11/142 (2013.01) [G06F 9/5077 (2013.01); G06F 11/0709 (2013.01); G06F 11/203 (2013.01); H04L 41/0668 (2013.01); G06F 9/4881 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for node management, performed by a computer device, the method comprising:
obtaining, in response to an abnormal processing node in a processing node cluster being detected, abnormal status information of the abnormal processing node, wherein the processing node cluster comprises a plurality of processing nodes and is associated with a data processing task, and the plurality of processing nodes are configured to collaboratively perform the data processing task;
in response to the abnormal status information satisfying a condition, enabling an auxiliary node outside the processing node cluster to replace the abnormal processing node;
in response to enabling the auxiliary node, adjusting an execution policy of the data processing task, the execution policy being used for indicating a processing manner of the data processing task and comprising a secondary computing policy, the secondary computing policy being a policy in which the auxiliary node re-performs a data processing sub-task with lost processed data reported by the abnormal processing node;
distributing data processing sub-tasks to the auxiliary node and remaining processing nodes based on the execution policy, the remaining processing nodes being processing nodes in the processing node cluster other than the abnormal processing node; and
transmitting task execution instructions to the auxiliary node and the remaining processing nodes, the task execution instructions being used for instructing the auxiliary node and the remaining processing nodes to perform the corresponding data processing sub-tasks.