US 12,229,036 B2
Automatically controlling resource partitions in advance of predicted bottlenecks for log streaming messages
Yue Wang, Beijing (CN); Yun Chen, Beijing (CN); Xiao Hai Ma, Beijing (CN); Yuan Hu, Beijing (CN); and Ze Zhang, Beijing (CN)
Assigned to INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Sep. 15, 2021, as Appl. No. 17/475,583.
Prior Publication US 2023/0083701 A1, Mar. 16, 2023
Int. Cl. G06F 11/34 (2006.01); G06F 9/50 (2006.01); G06F 9/54 (2006.01); G06F 11/07 (2006.01); G06F 11/30 (2006.01); G06F 9/455 (2018.01); G06F 11/00 (2006.01)
CPC G06F 11/3433 (2013.01) [G06F 9/5055 (2013.01); G06F 9/542 (2013.01); G06F 11/0793 (2013.01); G06F 11/3006 (2013.01); G06F 11/3428 (2013.01); G06F 11/3466 (2013.01); G06F 9/45558 (2013.01); G06F 2009/4557 (2013.01); G06F 9/5077 (2013.01); G06F 9/5083 (2013.01); G06F 11/004 (2013.01); G06F 2209/5017 (2013.01); G06F 2209/5019 (2013.01); G06F 2209/508 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for allocating computing resources, the computer-implemented method comprising:
generating, using a processor, tracing data that results from message traffic processed through multiple message paths by the processor;
analyzing, using the processor, the tracing data to generate;
service relationships associated with log streaming messages that generate the message traffic; and
service call chains disassembled from the service relationships and associated with the log streaming messages that generate the message traffic;
using the processor to use the service relationships, the service call chains, message size data, and topic data to generate a service and message tree operable to represent relationships between services, the topic data, and the message size data;
using the service and message tree to identify a predicted bottleneck path among the multiple message paths, wherein the predicted bottleneck path comprises at least one of the multiple message paths on which a message bottleneck is predicted to occur; and
allocating computer resources to the predicted bottleneck path before the predicted message bottleneck occurs.