US 11,677,818 B2
Multi-cluster ingress
Manjot Pahwa, Mountain View, CA (US); Matthew Delio, Mountain View, CA (US); Bowei Du, Mountain View, CA (US); Rohit Ramkumar, Mountain View, CA (US); Nikhil Jindal, Mountain View, CA (US); and Christian Bell, Mountain View, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Dec. 29, 2020, as Appl. No. 17/137,343.
Application 17/137,343 is a continuation of application No. 16/372,220, filed on Apr. 1, 2019, granted, now 10,887,380, issued on Jan. 5, 2021.
Prior Publication US 2021/0120079 A1, Apr. 22, 2021
Int. Cl. H04L 67/1021 (2022.01); H04L 67/01 (2022.01); G06F 9/50 (2006.01); H04L 67/02 (2022.01); H04L 67/10 (2022.01); H04L 67/1023 (2022.01); H04L 67/00 (2022.01)
CPC H04L 67/1021 (2013.01) [G06F 9/5083 (2013.01); H04L 67/01 (2022.05); H04L 67/02 (2013.01); H04L 67/10 (2013.01); H04L 67/1023 (2013.01); H04L 67/34 (2013.01)] 22 Claims
OG exemplary drawing
 
1. A computer-implemented method when executed by data processing hardware causes the data processing hardware to perform operations comprising:
receiving, from one or more clients, a plurality of application level requests directed to a software application hosted on multiple regional zones of a distributed system, each regional zone of the multiple regional zones comprising a corresponding cluster of container pods defining a respective node group, the corresponding cluster comprising at least one container pod executing the software application;
routing, using a Uniform Resource Locator (URL) mapping, one or more application level requests of the plurality of application level requests to the respective node group of the corresponding cluster of a particular regional zone among the multiple regional zones based on a geographical location and the software application associated with the one or more of the application level requests;
determining that the at least one container pod executing the software application of the corresponding cluster of the particular regional zone is unable to satisfy a traffic load associated with the one or more application level requests routed to the respective node group of the corresponding cluster of the particular regional zone;
based on determining that the at least one container pod executing the software application of the corresponding cluster of the particular regional zone is unable to satisfy the traffic load associated with the one or more application level requests routed to the respective node group of the corresponding cluster of the particular regional zone, scaling the respective node group of the corresponding cluster of the particular regional zone by instantiating one or more new container pods at the corresponding cluster of the particular regional zone to support the traffic load associated with the one or more application level requests; and
after scaling the respective node group of the corresponding cluster of the particular regional zone, synchronizing data between the corresponding clusters of each regional zone of the multiple regional zones.